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. 23-RESID-POST-AA
    6. 130925
    Prev
    Next
    INDEX
    Explanations

    RR

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Tudor
    -0.08
     /**<
    -0.08
    -bordered
    -0.08
     corona
    -0.08
     parmesan
    -0.07
     Dorset
    -0.07
     schwarz
    -0.07
     citrate
    -0.07
     anus
    -0.07
     repe
    -0.07
    POSITIVE LOGITS
     män
    0.08
    .Work
    0.08
     rod
    0.08
     screenshots
    0.08
     rods
    0.08
     Features
    0.07
    veillance
    0.07
    Human
    0.07
     forme
    0.07
     Entrepreneurs
    0.07
    Activations Density 0.001%

    No Known Activations