© 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. 30949
    Prev
    Next
    INDEX
    Explanations

    function

    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
    ，加
    -0.08
     Add
    -0.08
     المواد
    -0.07
     Bulk
    -0.07
    .Supplier
    -0.07
    Absent
    -0.07
    .Axis
    -0.07
     longitudinal
    -0.07
    .Fr
    -0.07
    Bulk
    -0.07
    POSITIVE LOGITS
     chatbot
    0.09
     interf
    0.08
    세계
    0.08
    执行
    0.08
     स्मार्ट
    0.08
    Sandbox
    0.07
    विश्व
    0.07
     sandbox
    0.07
    ruz
    0.07
    undos
    0.07
    Activations Density 0.006%

    No Known Activations