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. 53143
    Prev
    Next
    INDEX
    Explanations

    Parmenides

    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
    magn
    -0.09
     itching
    -0.08
     nyl
    -0.08
    lük
    -0.08
     Installing
    -0.08
     washers
    -0.08
    κών
    -0.07
    purple
    -0.07
    -0.07
     dirt
    -0.07
    POSITIVE LOGITS
     terv
    0.08
    Ts
    0.08
     fur
    0.07
    ాడ
    0.07
     permettre
    0.07
     زمان
    0.07
    (Stream
    0.07
     computational
    0.07
     Qu
    0.07
     fuori
    0.07
    Activations Density 0.000%

    No Known Activations