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. 11-RESID-POST-AA
    6. 88308
    Prev
    Next
    INDEX
    Explanations

    guiding the eye

    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
    .problem
    -0.08
    Reports
    -0.08
    _REPORT
    -0.07
     Report
    -0.07
    _report
    -0.07
    .name
    -0.07
    ack
    -0.07
    yak
    -0.07
    agam
    -0.07
     রিপোর্ট
    -0.07
    POSITIVE LOGITS
     പോക
    0.09
     trails
    0.09
     audience
    0.09
     irresist
    0.09
     trail
    0.09
     يشعر
    0.08
     눈
    0.08
     menuju
    0.08
     الجمهور
    0.08
     wearer
    0.08
    Activations Density 0.004%

    No Known Activations