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. 114013
    Prev
    Next
    INDEX
    Explanations

    patron deities

    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
     என்ப
    -0.07
    �
    -0.07
    Infinity
    -0.07
     의료
    -0.07
     dawn
    -0.07
    ZS
    -0.07
     kindness
    -0.07
     apopt
    -0.07
     пен
    -0.07
    .patient
    -0.07
    POSITIVE LOGITS
     پلان
    0.09
     protect
    0.08
     secured
    0.08
     zašč
    0.08
     حفاظت
    0.08
     خطة
    0.08
     prag
    0.08
     Saint
    0.08
     دفاع
    0.08
     *.
    0.08
    Activations Density 0.003%

    No Known Activations