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. 43170
    Prev
    Next
    INDEX
    Explanations

    ratios

    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
     etree
    -0.08
    ضة
    -0.08
    uffles
    -0.07
    xtures
    -0.07
    けば
    -0.07
     G
    -0.07
     నిర
    -0.07
     баз
    -0.07
    bracht
    -0.07
    ientation
    -0.07
    POSITIVE LOGITS
    နှ
    0.07
     sterile
    0.07
    agena
    0.07
    ei
    0.07
     traumatic
    0.07
     seamless
    0.07
     instance
    0.07
    loss
    0.07
     one's
    0.07
    ண்ண
    0.07
    Activations Density 0.012%

    No Known Activations