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. 12981
    Prev
    Next
    INDEX
    Explanations

    Video game roles/damage

    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
     surveyed
    -0.09
    _inventory
    -0.08
     Scout
    -0.08
     Inventory
    -0.08
     Español
    -0.08
     '..
    -0.08
     INVENT
    -0.08
     żad
    -0.08
     Dug
    -0.08
    okken
    -0.08
    POSITIVE LOGITS
    optimization
    0.08
     maximizing
    0.08
    imax
    0.08
     skyscr
    0.08
     sax
    0.08
     driver
    0.08
    -heavy
    0.08
     steig
    0.07
     married
    0.07
    gender
    0.07
    Activations Density 0.003%

    No Known Activations