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. 112033
    Prev
    Next
    INDEX
    Explanations

    Data analysis/machine learning

    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
     Nat
    -0.08
    Nat
    -0.08
     사람들이
    -0.08
    女子
    -0.08
    -0.08
    Julie
    -0.08
    Faces
    -0.08
    Joseph
    -0.08
     traveling
    -0.08
    Movies
    -0.08
    POSITIVE LOGITS
     renovation
    0.10
     পরীক্ষা
    0.09
     যাচ
    0.09
     بررسی
    0.09
     обработ
    0.08
     분석
    0.08
     analysis
    0.08
     سازی
    0.08
     definir
    0.08
     análise
    0.08
    Activations Density 0.474%

    No Known Activations