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. 60663
    Prev
    Next
    INDEX
    Explanations

    Currency symbols

    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
     иннова
    -0.08
     bureaucr
    -0.08
     Diocese
    -0.08
     Direito
    -0.08
     Escola
    -0.08
    ficie
    -0.08
    Hw
    -0.08
     bureaucracy
    -0.08
    fone
    -0.08
     Error
    -0.08
    POSITIVE LOGITS
    inerary
    0.10
    住宿
    0.09
     unterwegs
    0.09
     খাব
    0.09
     refeições
    0.09
    餐
    0.09
     রাত
    0.08
     भोजन
    0.08
    گذاری
    0.08
     lunch
    0.08
    Activations Density 0.020%

    No Known Activations