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. 392
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    ಪ್ರ
    -0.08
     og
    -0.07
     SH
    -0.07
    ೆಗೆ
    -0.07
     donuts
    -0.07
     dicha
    -0.07
     świet
    -0.07
     vise
    -0.07
     אור
    -0.07
     asked
    -0.07
    POSITIVE LOGITS
     Ath
    0.08
     Bron
    0.08
     Seminar
    0.08
     wom
    0.08
     चाहे
    0.08
    riana
    0.08
    reman
    0.07
    提醒
    0.07
     Gle
    0.07
     Belmont
    0.07
    Activations Density 0.010%

    No Known Activations