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. 43237
    Prev
    Next
    INDEX
    Explanations

    Overview

    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
     obligatoire
    -0.07
     welding
    -0.07
     Barre
    -0.07
    -State
    -0.07
     Etats
    -0.07
     sext
    -0.07
     nere
    -0.07
     akkurat
    -0.07
     Billboard
    -0.07
     school's
    -0.07
    POSITIVE LOGITS
    概要
    0.08
     उद्देश्य
    0.08
    _te
    0.08
    摘要
    0.08
    Te
    0.08
     Te
    0.08
     teaser
    0.08
    래
    0.07
    概
    0.07
    leme
    0.07
    Activations Density 0.013%

    No Known Activations