© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44836
    Prev
    Next
    INDEX
    Explanations

    News articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     house
    -0.09
    ासा
    -0.09
     reserves
    -0.08
     आंक
    -0.08
     खाने
    -0.08
    uis
    -0.08
    েধ
    -0.08
    ैल
    -0.07
     conhe
    -0.07
     Reserve
    -0.07
    POSITIVE LOGITS
     undergo
    0.09
    ，他们
    0.09
     పొంద
    0.08
     receive
    0.08
    mitt
    0.08
     ورکړ
    0.08
     möjlighet
    0.08
     exposed
    0.08
     получают
    0.08
     Deutsche
    0.08
    Activations Density 0.246%

    No Known Activations