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. 102781
    Prev
    Next
    INDEX
    Explanations

    BMW, Mercedes-Benz series

    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
     rooting
    -0.09
     lek
    -0.08
     graffiti
    -0.08
     పోస్ట
    -0.08
     subsidy
    -0.08
     grazing
    -0.08
    лл
    -0.08
     lesson
    -0.08
    733
    -0.08
     maize
    -0.07
    POSITIVE LOGITS
     sedan
    0.12
    舒
    0.09
     élégant
    0.09
     Sedan
    0.09
     उत्कृष्ट
    0.09
     elegantly
    0.09
    卧
    0.08
     комфорт
    0.08
    宁
    0.08
    comfortable
    0.08
    Activations Density 0.014%

    No Known Activations