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. 11951
    Prev
    Next
    INDEX
    Explanations

    Period

    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
     (...
    -0.08
     Pense
    -0.08
     Russell
    -0.07
     Lebens
    -0.07
     rigor
    -0.07
    imoto
    -0.07
     Sterling
    -0.07
     speculate
    -0.07
    [...]↵↵
    -0.07
     należy
    -0.07
    POSITIVE LOGITS
    Looks
    0.08
    .Total
    0.08
     mostly
    0.08
    Таким
    0.08
     모두
    0.08
    Seems
    0.07
    Totals
    0.07
     basically
    0.07
     mainly
    0.07
    なので
    0.07
    Activations Density 0.060%

    No Known Activations