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. 98396
    Prev
    Next
    INDEX
    Explanations

    Mix of languages/symbols

    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
     Aachen
    -0.08
     umo
    -0.08
     Dresden
    -0.08
    ഹ
    -0.08
     filament
    -0.07
     Berlin
    -0.07
     oferecem
    -0.07
    ोड
    -0.07
    _fil
    -0.07
     vám
    -0.07
    POSITIVE LOGITS
    -code
    0.08
    respect
    0.08
    ryt
    0.08
    waga
    0.08
     Scoped
    0.08
    igest
    0.08
    uesta
    0.07
    arken
    0.07
    卖
    0.07
     entreten
    0.07
    Activations Density 0.001%

    No Known Activations