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. 60718
    Prev
    Next
    INDEX
    Explanations

    originally

    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
     pagpap
    -0.08
     Beck
    -0.08
     പത
    -0.08
     pendant
    -0.07
     মাত্র
    -0.07
     അവത
    -0.07
     Karin
    -0.07
    stab
    -0.07
     Handel
    -0.07
     encouraged
    -0.07
    POSITIVE LOGITS
    ẵn
    0.08
     '''↵
    0.08
     carácter
    0.08
     ')↵
    0.08
    örd
    0.08
     нез
    0.08
     прошлого
    0.08
     ગ્રામ
    0.08
    attanooga
    0.08
    нинг
    0.07
    Activations Density 0.003%

    No Known Activations