Sourcepreprinttext stored

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines

Jørgensen, Mikkel Godsk, Hansen, Lars KaiarXiv.orgPublished May 29, 2026Original︎ ↗Archived copy

Claims2

ExaminationsNone

TextStored, not divided

VersionsOne known

CopiesNone recorded

CorrectionsNone recorded

Facts checked Nov 12, 2026

ReachNo copies recorded

StructureIn 2 claims' maps0 sources downstream across 2 claims

EvidenceNot yet read

ReviewsNot reviewed

Examinations

None recorded. An examination is commissioned by a claim’s Steward for what its claim rests on; a review of the document for its own sake is asked for as a request bearing on it.

Text

Stored, not yet divided into passages.

As quoted

We find that Sparse Autoencoders can, in fact, perform close to on par with the reference LoRA performance on the AxBench benchmark, when features are selected and labelled with our supervised pipeline.

Under what conditions, if any, do sparse-autoencoder and other dictionary-learning features outperform linear probes and difference-of-means steering on labeled language-model tasks?Unassessed

Not yet read by this claim’s Steward.

As quoted

This work serves as a partial rebuttal for Sparse Autoencoders and suggests that the results of Wu et al. (2025) did not do them full justice. We find that Sparse Autoencoders can, in fact, perform close to on par with the reference LoRA performance on the AxBench benchmark, when features are selected and labelled with our supervised pipeline.

On AxBench, SAE steering underperforms both prompting and difference-in-means representations.Verifiedmentions

Not yet read by this claim’s Steward.

Lineage across 2 claims

Draws on · none recorded

This source

Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines

in 2 claims' maps

Drawn on by · none recorded

Record

Kind: preprint
Authors: Jørgensen, Mikkel Godsk, Hansen, Lars Kai
Publisher: arXiv.org
Published: May 29, 2026
DOI: None
Link: https://arxiv.org/abs/2605.31183
Archived copy: https://web.archive.org/web/20261027132441/https://arxiv.org/abs/2605.31183
Stored text: 4,622 characters, retrieved Nov 12, 2026 · not yet divided
Claims extracted: Not recorded
Versions: One known
Copies: None recorded
Corrections: None recorded
Facts checked: Nov 12, 2026

History 2

Nov 12, 2026FactsFacts fetcher · Facts looked up
Nov 12, 2026Entered the graphEntered the graph; copy stored