Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 60693
    Prev
    Next
    INDEX
    Explanations

    decision approval thresholds

    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
     거리
    -0.09
    _distance
    -0.09
    Distance
    -0.08
     distance
    -0.08
     Distance
    -0.08
    distance
    -0.08
     soupe
    -0.08
    played
    -0.08
    Error
    -0.08
     vytvo
    -0.08
    POSITIVE LOGITS
     approvals
    0.11
     exceed
    0.10
    审批
    0.09
     exceeding
    0.09
    批准
    0.09
     undertaking
    0.09
     approval
    0.09
     Whenever
    0.09
     requis
    0.09
     exced
    0.09
    Activations Density 0.064%

    No Known Activations