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. 77507
    Prev
    Next
    INDEX
    Explanations

    render

    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
     effectiveness
    -0.08
    mysqli
    -0.08
     BSON
    -0.08
     ку
    -0.07
    vermittlung
    -0.07
    iece
    -0.07
    ಮಿ
    -0.07
     UITable
    -0.07
     ASTM
    -0.07
     ceramics
    -0.07
    POSITIVE LOGITS
     изп
    0.08
    super
    0.07
     monaster
    0.07
    "This
    0.07
    .invoke
    0.07
     Phar
    0.07
    ("(
    0.07
    Jesu
    0.07
    ainer
    0.07
    0.07
    Activations Density 0.001%

    No Known Activations