Claimempirical · verifiableA factual claim that could be checked directly against observation or primary records.constitution →importance · minorImportance 0.40, from 0 to 1 · minor: narrow or largely settled, cheap to get right. Higher-importance claims are worth more to assess, so funding reaches them sooner.constitution →

TopicsMechanistic Interpretability Latent Knowledge in Language Models

Delta-Crosscoder recovered causally validated latents across all ten tested organisms, compared with six for DSF and four to five for BatchTopK.

Not yet assessed, so this page carries no verdict. That is not a finding for or against the claim. Attention goes where its expected value is highest and someone funds it; nothing has funded an assessment of this claim yet, and anyone can.

Decomposition

This claim has not been assessed yet. Attention goes where its expected value is highest and someone funds it; once this claim's assessment is funded and runs, it may well decompose into subclaims.

or start a mandate for this whole area →

Provenance

Where this claim has been said, linked to its canonical form.

Its one source has been traced to an origin, or to one another.

As shown in Figure 5, Delta-Crosscoder recovers behav- iorally relevant latents for all 10 organisms. DSF succeeds on 6 organisms, including Taboo, Subliminal Learning, the SDF Kansas Abortion case, and EM of Qwen Model.

Delta-Crosscoder: Robust Crosscoder Model Diffing in Narrow Fine-Tuning Regimespreprintextraction 0.80

Kassem, Aly et al. · arXiv.org · Feb 16, 2026 · original

Section 6.1 comparison to SAE-based diffing baselines (DSF, BatchTopK-200, BatchTopK-400); success = a recovered latent passes causal validation via steering and max-activation analysis.

Cite this claim: a formal citation with its evidence attached

Embed this claim: show it on another site with its current assessment

An embed reports the graph's judgment as it stands when the page is viewed: the status with its confidence, how disputed the claim is, and the date. It links back here.

CardFits its column and sizes itself. Without the script it stays a quotation with its link.

<blockquote class="minerval-claim" data-claim-id="f4abd3d9-5846-4aa2-b795-db1166b72346"><a href="https://minerval.ai/claims/f4abd3d9-5846-4aa2-b795-db1166b72346">Delta-Crosscoder recovered causally validated latents across all ten tested organisms, compared with six for DSF and four to five for BatchTopK.</a></blockquote>
<script async src="https://minerval.ai/embed.js"></script>

IframeWhere scripts are not allowed. A fixed height; add ?theme=light or ?theme=dark to fix its colours.

<iframe src="https://minerval.ai/embed/claims/f4abd3d9-5846-4aa2-b795-db1166b72346" title="Minerval: Delta-Crosscoder recovered causally validated latents across all ten tested organisms, co…" width="480" height="225" style="border:0;max-width:100%" loading="lazy"></iframe>

BadgeAn image for a README or a forum post, in Markdown.

[![Minerval's judgment of this claim](https://minerval.ai/embed/claims/f4abd3d9-5846-4aa2-b795-db1166b72346/badge.svg)](https://minerval.ai/claims/f4abd3d9-5846-4aa2-b795-db1166b72346)

The badge now:

Contribute

Every judgment on this page is open to challenge. A contribution is evaluated on its merits by the reviewer; if it succeeds the page changes, and if it does not, the reasons are stated. Either way the exchange becomes part of the claim’s public record.

Stated views None yet. A view stated to the graph is shown on this page in its speaker’s words, as a source like any other, and carries no weight in the assessment.

Created by extractor · Nov 13, 2026. Every judgment on this page is accompanied by a reasoning trace.