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. 108999
    Prev
    Next
    INDEX
    Explanations

    Frame

    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
     Mit
    -0.08
     cave
    -0.08
     dispute
    -0.08
    ibar
    -0.08
     Cave
    -0.08
    狼
    -0.07
     Mississippi
    -0.07
     nagpap
    -0.07
     mit
    -0.07
    еред
    -0.07
    POSITIVE LOGITS
    ,column
    0.07
    ਜੇ
    0.07
    way
    0.07
    (columns
    0.07
     toppings
    0.07
    ోగ
    0.07
    ODB
    0.07
    ਵੇ
    0.07
    bd
    0.07
    дов
    0.07
    Activations Density 0.002%

    No Known Activations