© 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. 94945
    Prev
    Next
    INDEX
    Explanations

    frequency

    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
    .bio
    -0.09
     رسم
    -0.07
     بص
    -0.07
     Highlights
    -0.07
    _dim
    -0.07
    ْ
    -0.07
    _Draw
    -0.07
    eny
    -0.07
    Nord
    -0.07
     PEN
    -0.07
    POSITIVE LOGITS
     tally
    0.08
     pratiquer
    0.08
     abusing
    0.08
    百分
    0.08
     olaraq
    0.08
    _literals
    0.08
    夕
    0.08
     pract
    0.07
     comportements
    0.07
     behand
    0.07
    Activations Density 0.009%

    No Known Activations