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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109125
    Prev
    Next
    INDEX
    Explanations

    Math and calculus

    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
     perifer
    -0.10
     boyunca
    -0.08
     Peripheral
    -0.07
     تحد
    -0.07
     extremist
    -0.07
     mx
    -0.07
    (crate
    -0.07
     democracia
    -0.07
    -0.07
     Gum
    -0.07
    POSITIVE LOGITS
    一下
    0.09
     cleverly
    0.09
     Betracht
    0.09
     maths
    0.09
    -based
    0.08
     approach
    0.08
     math
    0.08
     mathematics
    0.08
    -Based
    0.08
     hyvä
    0.08
    Activations Density 0.056%

    No Known Activations