© 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. 108745
    Prev
    Next
    INDEX
    Explanations

    data columns

    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
     Frederick
    -0.07
    建议
    -0.07
    .Infof
    -0.07
    une
    -0.07
     עומ
    -0.07
     suggestions
    -0.07
    قى
    -0.07
    _th
    -0.07
    cenes
    -0.07
    动力
    -0.07
    POSITIVE LOGITS
    Across
    0.10
     across
    0.10
     Across
    0.09
    coeff
    0.09
    [`
    0.09
     family's
    0.09
    [:,:,
    0.09
     coeff
    0.09
     pnl
    0.09
     coefficients
    0.08
    Activations Density 0.016%

    No Known Activations