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. 112121
    Prev
    Next
    INDEX
    Explanations

    agar

    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
    或者
    -0.08
    ੌ
    -0.08
    ौल
    -0.08
     Immun
    -0.07
     افز
    -0.07
    òa
    -0.07
    స్ట
    -0.07
     Fahrenheit
    -0.07
    ே
    -0.06
    应该
    -0.06
    POSITIVE LOGITS
    cliffe
    0.08
    dito
    0.08
     iom
    0.07
     desafio
    0.07
    antic
    0.07
    tractive
    0.07
     midst
    0.07
     Cupid
    0.07
    /reference
    0.07
    within
    0.07
    Activations Density 0.204%

    No Known Activations