Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-RESID-POST-AA
    6. 19038
    Prev
    Next
    INDEX
    Explanations

    Math/logic problems with cases

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     usually
    -0.09
     needs
    -0.08
     …
    -0.08
     shouldn
    -0.08
    ometimes
    -0.07
    ınızı
    -0.07
     gotta
    -0.07
    usually
    -0.07
     need
    -0.07
     probably
    -0.07
    POSITIVE LOGITS
     treasure
    0.08
     hiç
    0.08
     offiziellen
    0.08
     cố
    0.08
     регулиру
    0.08
     ಅಧಿಕ
    0.07
    .jump
    0.07
    .toolbox
    0.07
     какой
    0.07
     thắng
    0.07
    Activations Density 0.053%

    No Known Activations