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. 60820
    Prev
    Next
    INDEX
    Explanations

    math formulas

    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
     մ
    -0.08
    ерх
    -0.08
     rir
    -0.08
     AM
    -0.08
    -0.07
    ,这
    -0.07
     crema
    -0.07
    arant
    -0.07
     necesitar
    -0.07
     바라
    -0.07
    POSITIVE LOGITS
    oks
    0.08
    hedron
    0.08
    �
    0.07
    -fold
    0.07
     diversas
    0.07
    wyr
    0.07
     mimic
    0.07
     Preschool
    0.07
    ick
    0.07
     मु
    0.07
    Activations Density 0.000%

    No Known Activations