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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 113836
    Prev
    Next
    INDEX
    Explanations

    lead forms

    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
    awasan
    -0.08
     לאורך
    -0.08
     finit
    -0.08
    END
    -0.08
     antim
    -0.08
    াদ
    -0.08
     anh
    -0.08
    Fails
    -0.08
    ‫
    -0.07
     pervers
    -0.07
    POSITIVE LOGITS
     Callback
    0.09
     Extract
    0.08
    -helper
    0.08
    _fields
    0.08
    مولة
    0.08
    实名
    0.08
     सुविधा
    0.07
     Vessel
    0.07
     Bho
    0.07
     thao
    0.07
    Activations Density 0.003%

    No Known Activations