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. 109728
    Prev
    Next
    INDEX
    Explanations

    Literary characters and works

    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
     daran
    -0.08
    अन
    -0.07
    >s
    -0.07
    lə
    -0.07
    lər
    -0.07
     coinc
    -0.07
     dais
    -0.07
    별
    -0.07
    lərinə
    -0.07
    Bạn
    -0.07
    POSITIVE LOGITS
     เป็นต้น
    0.08
    izy
    0.08
     Aunque
    0.08
     Embora
    0.08
     obviamente
    0.08
    (express
    0.07
    icies
    0.07
    .init
    0.07
     Oficial
    0.07
    isco
    0.07
    Activations Density 0.161%

    No Known Activations