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. 94965
    Prev
    Next
    INDEX
    Explanations

    dynamic

    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
     heuristic
    -0.07
     Paperback
    -0.07
     librarian
    -0.07
     empirical
    -0.07
     snapshots
    -0.07
     Landmark
    -0.07
     uta
    -0.07
     lace
    -0.07
     verdict
    -0.07
     OLD
    -0.07
    POSITIVE LOGITS
     accommodate
    0.08
     واسع
    0.08
     balance
    0.08
     naturel
    0.08
     풍
    0.08
     alami
    0.07
     wy
    0.07
    九
    0.07
     كبير
    0.07
     omstandigheden
    0.07
    Activations Density 0.001%

    No Known Activations