© 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. 19-RESID-POST-AA
    11. 102907
    Prev
    Next
    INDEX
    Explanations

    vector operations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    وأكد
    -0.10
    旗舰厅
    -0.09
    开户链接
    -0.09
    ultiple
    -0.09
     tenei
    -0.09
    铁算盘
    -0.09
    اهرات
    -0.09
    提现吗
    -0.09
    Bydd
    -0.09
    直营网
    -0.09
    POSITIVE LOGITS
     [(
    0.10
     vector
    0.09
     ((
    0.09
     function
    0.08
     vertex
    0.08
     coordinates
    0.08
     gives
    0.08
    =((
    0.08
    (vertex
    0.08
    ;
    0.08
    Activations Density 0.009%

    No Known Activations