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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 11-RESID-POST-AA
    6. 58482
    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
    conc
    -0.08
    rote
    -0.08
    sf
    -0.08
     ಬಿಡುಗಡೆ
    -0.08
     Yukon
    -0.07
     מלא
    -0.07
    city
    -0.07
     والر
    -0.07
    apa
    -0.07
    flag
    -0.07
    POSITIVE LOGITS
     Karma
    0.08
     siglos
    0.08
     nanos
    0.08
     behalve
    0.08
     IOException
    0.08
     antig
    0.08
     daim
    0.07
     lombok
    0.07
    ље
    0.07
    .Clone
    0.07
    Activations Density 0.000%

    No Known Activations