© 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. 64896
    Prev
    Next
    INDEX
    Explanations

    non-English text

    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
    割
    -0.08
    -0.08
    際
    -0.08
    /tool
    -0.07
    ଧ
    -0.07
    ધ
    -0.07
    ଥ
    -0.07
    际
    -0.07
    -0.07
     crowded
    -0.07
    POSITIVE LOGITS
    fulness
    0.10
    Enough
    0.09
     sentimento
    0.09
     prosperity
    0.09
    _kensho
    0.09
     والسلام
    0.08
     качества
    0.08
    ุมวิท
    0.08
    headed
    0.08
     Paraguay
    0.08
    Activations Density 0.041%
    No Known Activations