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. 60463
    Prev
    Next
    INDEX
    Explanations

    statistical analysis reporting

    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
     Military
    -0.08
    coach
    -0.08
    (""+
    -0.08
     lily
    -0.08
    Military
    -0.08
     refrigerator
    -0.08
     specialties
    -0.08
    (payload
    -0.07
    *(-
    -0.07
     Specialist
    -0.07
    POSITIVE LOGITS
     goed
    0.09
    _table
    0.09
     table
    0.09
    .GUI
    0.08
     recomend
    0.08
     indicative
    0.08
    .table
    0.08
    Table
    0.08
     UIApplication
    0.08
     prepor
    0.08
    Activations Density 0.003%

    No Known Activations