Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29919
    Prev
    Next
    INDEX
    Explanations

    writing creative descriptions

    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
     Hospice
    -0.08
    ldb
    -0.08
    ක්
    -0.08
     ie
    -0.08
    lex
    -0.07
    胞
    -0.07
     Concept
    -0.07
     Examine
    -0.07
     Inputs
    -0.07
    ෙක්
    -0.07
    POSITIVE LOGITS
    .↵↵↵↵
    0.09
    。↵↵↵↵
    0.08
    ."
    0.08
    Peso
    0.08
    Packed
    0.08
     cohes
    0.07
     distorted
    0.07
     cuc
    0.07
     وإ
    0.07
    ?↵↵↵↵
    0.07
    Activations Density 0.066%

    No Known Activations