© 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. 29709
    Prev
    Next
    INDEX
    Explanations

    baking

    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
    helves
    -0.09
     blauwe
    -0.09
     Surviv
    -0.09
     Survivor
    -0.09
     야
    -0.09
     survivors
    -0.08
     TY
    -0.08
    ，坚持
    -0.08
     Viewing
    -0.08
     igbesi
    -0.08
    POSITIVE LOGITS
    acting
    0.09
     baked
    0.09
     explosive
    0.08
     doping
    0.08
     pronounced
    0.08
     attacking
    0.07
     spawn
    0.07
     baking
    0.07
     playful
    0.07
     acting
    0.07
    Activations Density 0.004%

    No Known Activations