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. 65656
    Prev
    Next
    INDEX
    Explanations

    etc

    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
    真人
    -0.08
    ří
    -0.08
    ledon
    -0.08
     Chau
    -0.07
     Marco
    -0.07
     fires
    -0.07
    thorn
    -0.07
    丈夫
    -0.07
    <P
    -0.07
    _fire
    -0.07
    POSITIVE LOGITS
     екенін
    0.10
     патраб
    0.09
     depending
    0.08
    ไหน
    0.08
     요구
    0.08
     требований
    0.08
    (size
    0.07
     esigenze
    0.07
    urface
    0.07
    requirements
    0.07
    Activations Density 0.042%

    No Known Activations