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. 43973
    Prev
    Next
    INDEX
    Explanations

    blast

    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
    jaz
    -0.08
    tum
    -0.08
    jx
    -0.08
    eva
    -0.08
    Torrent
    -0.08
     же
    -0.08
     Sar
    -0.07
    亚
    -0.07
    毁
    -0.07
     opl
    -0.07
    POSITIVE LOGITS
     bron
    0.07
     verb
    0.07
    abwe
    0.07
    走
    0.07
    ধ
    0.07
    924
    0.07
     kul
    0.07
    ೆ
    0.07
     quo
    0.07
     offici
    0.07
    Activations Density 0.006%

    No Known Activations