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. 76098
    Prev
    Next
    INDEX
    Explanations

    is

    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
     Effekt
    -0.08
     spe
    -0.08
     ڇ
    -0.08
    Spe
    -0.08
    ట్టు
    -0.08
    lingen
    -0.08
    him
    -0.08
    эфф
    -0.07
     Tem
    -0.07
     عمليات
    -0.07
    POSITIVE LOGITS
     byd
    0.09
    Author
    0.08
     ulaş
    0.08
    Color
    0.08
     warranty
    0.08
    .pi
    0.07
     maths
    0.07
     색
    0.07
     warranties
    0.07
    .answer
    0.07
    Activations Density 0.009%

    No Known Activations