© 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. 95246
    Prev
    Next
    INDEX
    Explanations

    Mo, ium

    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
     abz
    -0.08
     sommet
    -0.08
     콘
    -0.08
     コン
    -0.08
     Canterbury
    -0.08
     bald
    -0.08
     conservatives
    -0.08
     "#"
    -0.07
     priests
    -0.07
    企
    -0.07
    POSITIVE LOGITS
    .rpc
    0.09
    PNG
    0.08
    Bos
    0.08
    Eth
    0.08
    Lag
    0.08
    _png
    0.08
     Yii
    0.08
    Laravel
    0.07
     асп
    0.07
    crop
    0.07
    Activations Density 0.002%

    No Known Activations