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. 59473
    Prev
    Next
    INDEX
    Explanations

    best

    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
    amp
    -0.08
    ????????
    -0.07
    /application
    -0.07
    ضاف
    -0.07
     Sight
    -0.07
     handy
    -0.07
    uct
    -0.07
     container
    -0.07
    장의
    -0.07
     Auf
    -0.07
    POSITIVE LOGITS
    最佳
    0.10
     utmost
    0.10
     максимально
    0.10
     optimum
    0.09
     maximizing
    0.09
     optimale
    0.09
     máximo
    0.09
     maxim
    0.09
     optimaal
    0.09
     tối
    0.09
    Activations Density 0.036%

    No Known Activations