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. 43190
    Prev
    Next
    INDEX
    Explanations

    Lost-wax casting

    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
     betrekking
    -0.08
    LCD
    -0.08
    <=
    -0.08
     angesehen
    -0.08
    apea
    -0.08
     <=
    -0.07
     arrival
    -0.07
     lax
    -0.07
    作用
    -0.07
     pertenc
    -0.07
    POSITIVE LOGITS
     TNT
    0.09
    λύ
    0.08
    (火
    0.08
     Suzuki
    0.08
     मृत्यु
    0.08
     الموت
    0.08
     মৃত্য
    0.08
     Joker
    0.08
     burnout
    0.08
     火
    0.08
    Activations Density 0.002%

    No Known Activations