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. 44965
    Prev
    Next
    INDEX
    Explanations

    encoder

    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
     hung
    -0.08
     throttle
    -0.07
     patron
    -0.07
     máte
    -0.07
     وص
    -0.07
     Dyn
    -0.07
    _va
    -0.07
     bravo
    -0.07
     tat
    -0.07
     corporal
    -0.07
    POSITIVE LOGITS
    observer
    0.08
    0.08
    ιω
    0.08
     Buffet
    0.08
    רץ
    0.07
    -contract
    0.07
    -reader
    0.07
    aner
    0.07
    photos
    0.07
    .readline
    0.07
    Activations Density 0.001%

    No Known Activations