Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 23-RESID-POST-AA
    6. 130756
    Prev
    Next
    INDEX
    Explanations

    Mixed content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PPP
    -0.09
     PHPUnit
    -0.08
     Brasil
    -0.08
     Pong
    -0.08
    ังหว
    -0.07
     QObject
    -0.07
     minimo
    -0.07
     Immutable
    -0.07
     Sal
    -0.07
    PPP
    -0.07
    POSITIVE LOGITS
     stain
    0.09
    seed
    0.08
    isine
    0.08
    mul
    0.08
    EI
    0.08
     jardin
    0.08
    Greg
    0.07
    您的
    0.07
    .Adam
    0.07
    erva
    0.07
    Activations Density 0.002%

    No Known Activations