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. 106323
    Prev
    Next
    INDEX
    Explanations

    crown

    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
    .cwd
    -0.09
    hosting
    -0.08
    .constant
    -0.08
    buddy
    -0.07
    weile
    -0.07
     Lange
    -0.07
     moder
    -0.07
    lag
    -0.07
    Bas
    -0.07
    mer
    -0.07
    POSITIVE LOGITS
    สุด
    0.10
     glorious
    0.09
     сия
    0.09
    耀
    0.08
    ाकार
    0.08
    夺
    0.08
     glory
    0.08
    �
    0.08
     Dion
    0.08
     아름
    0.08
    Activations Density 0.005%

    No Known Activations