Skip to content
SN-X
All research
PaperAugust 21, 2025

Unknown-Unknown SAE Feature Discovery via Context-Differential Activation with Probe-Alignment Filtering

We describe the unknown-unknown SAE feature discovery workflow in MIVP. The workflow identifies SAE features that fire differentially between two contexts, then filters out features that are already explained by a registered probe via decoder-row cosine alignment. Surviving features are candidate hidden-behaviour features for human review.

M. TaylorSN-X
View on github · oca

1. Introduction

A registered probe is an instrumented concept. If a model is doing something we have not instrumented, the probes do not see it. Sparse autoencoder features are candidates for such concepts. A feature that fires differentially between contexts and is not explained by any registered probe is a candidate hidden-behaviour feature.

2. Background

Sparse autoencoders (Bricken et al., 2023; Cunningham et al., 2023; Templeton et al., 2024) are the de facto dictionary. Polysemanticity and superposition are studied by Elhage et al. (2022). Hidden-behaviour discovery is discussed by Hubinger et al. (2024).

3. Method

3.1 The Workflow

UnknownUnknownDiscovery takes an SAE, two context groups of activations, and the list of known probes. For each feature, the effect size is (mean_a − mean_b) / pooled_std. Features with effect below min_effect (default 1.0) are skipped.

3.2 The Decoder-Row Alignment Test

For each candidate feature, compute the cosine similarity between the SAE's decoder row and each known probe direction. Features with max_align > 0.7 are filtered out (already explained).

3.3 Structural Non-Gating Posture

As with the other T3 audits, the finding is experimental and E0.

4. Results

Evaluated on a synthetic SAE with a known concept injected as a sparse direction.

SettingTrue unknowns detectedFalse positives
1 known, 1 unknown1 / 10
5 known, 5 unknowns (low signal)3 / 50
5 known, 5 unknowns (high signal)5 / 50

5. Discussion

The max_align filter is the structural reason the workflow is useful and not just noisy. The workflow inherits all of the SAE's limits.

6. Conclusion

An unknown-unknown SAE feature discovery workflow that surfaces context-differential features not explained by registered probes.

References

Bricken et al. (2023). Anthropic. / Cunningham et al. (2023). ICLR. / Elhage et al. (2022). Anthropic. / Hubinger et al. (2024). arXiv. / Templeton et al. (2024). Anthropic.