© 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. 95368
    Prev
    Next
    INDEX
    Explanations

    35

    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
     뭐
    -0.09
    谁
    -0.08
     valu
    -0.08
     SCALE
    -0.08
     gaire
    -0.08
     Nearly
    -0.08
     sann
    -0.08
     כמעט
    -0.08
     ինձ
    -0.08
     leha
    -0.08
    POSITIVE LOGITS
    security
    0.08
    ensure
    0.08
    _br
    0.08
    brane
    0.08
    script
    0.08
     ब्र
    0.08
    ब्र
    0.08
    _BR
    0.08
    -br
    0.08
    ception
    0.08
    Activations Density 0.003%

    No Known Activations