© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 95227
    Prev
    Next
    INDEX
    Explanations

    factual information

    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
     Aub
    -0.08
    .uri
    -0.08
     winter
    -0.08
     hout
    -0.07
     Kate
    -0.07
     Paula
    -0.07
     sneeuw
    -0.07
     Honolulu
    -0.07
     aloha
    -0.07
     joul
    -0.07
    POSITIVE LOGITS
    ظ
    0.08
     عرضه
    0.08
    Se
    0.07
    .NET
    0.07
    enz
    0.07
    икан
    0.07
    ಣಿ
    0.07
    technik
    0.07
     Se
    0.07
     Testament
    0.07
    Activations Density 0.338%

    No Known Activations