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. 65309
    Prev
    Next
    INDEX
    Explanations

    goals and objectives

    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
     LS
    -0.08
    PLA
    -0.07
     interventions
    -0.07
     ct
    -0.07
     day
    -0.07
     č
    -0.07
    深入
    -0.07
     Lex
    -0.07
    ct
    -0.07
     jeopard
    -0.07
    POSITIVE LOGITS
     अश
    0.09
    оса
    0.08
    물이
    0.08
     loaders
    0.08
     BOR
    0.07
     שלהם
    0.07
     committees
    0.07
     bowls
    0.07
     ekip
    0.07
    /result
    0.07
    Activations Density 0.000%

    No Known Activations