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. 12113
    Prev
    Next
    INDEX
    Explanations

    workbook

    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
     beno
    -0.08
     Katz
    -0.08
     pré
    -0.08
     शिव
    -0.08
     notícias
    -0.08
     корм
    -0.07
    iction
    -0.07
    资讯
    -0.07
    asticsearch
    -0.07
     Maschinen
    -0.07
    POSITIVE LOGITS
     inteiro
    0.09
    -wide
    0.08
     absoluta
    0.07
     workbook
    0.07
     inteira
    0.07
    Duplicates
    0.07
    RARY
    0.07
     duplicates
    0.07
    ued
    0.07
     Workbook
    0.07
    Activations Density 0.002%

    No Known Activations