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. 112793
    Prev
    Next
    INDEX
    Explanations

    +

    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
    arhi
    -0.07
     Lots
    -0.07
     схема
    -0.07
    .batch
    -0.07
     האחרון
    -0.07
     slogan
    -0.07
    (print
    -0.07
    Nobody
    -0.07
    auft
    -0.07
     мәз
    -0.07
    POSITIVE LOGITS
    cla
    0.07
    �
    0.07
     squared
    0.07
     Willow
    0.07
     vigil
    0.07
    stu
    0.07
     Wrist
    0.07
     arti
    0.07
    (condition
    0.07
    mh
    0.07
    Activations Density 0.024%

    No Known Activations