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

    Neuronpedia

    APICircuit 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. 11989
    Prev
    Next
    INDEX
    Explanations

    99

    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
    evas
    -0.09
    ️
    -0.08
    ―
    -0.08
    ︎
    -0.08
     accordion
    -0.08
    。
    -0.07
     λί
    -0.07
    。...↵↵
    -0.07
    ;.
    -0.07
    .Â
    -0.07
    POSITIVE LOGITS
     puedan
    0.08
     certain
    0.08
     sausage
    0.07
    0.07
     den
    0.07
     structure
    0.07
    某
    0.07
     hong
    0.07
    structure
    0.07
     rip
    0.07
    Activations Density 0.226%

    No Known Activations