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. 106288
    Prev
    Next
    INDEX
    Explanations

    hyphen

    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
     Mercury
    -0.08
     Pri
    -0.07
     facilitator
    -0.07
    ie
    -0.07
    Pri
    -0.07
     apk
    -0.07
    reader
    -0.07
     dalje
    -0.07
    -reader
    -0.07
     Forestry
    -0.07
    POSITIVE LOGITS
    .Relative
    0.08
    odra
    0.08
    angang
    0.08
    verbose
    0.07
    ผล
    0.07
     JObject
    0.07
    эм
    0.07
     bern
    0.07
    烈
    0.07
    _uns
    0.07
    Activations Density 0.001%

    No Known Activations