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. 106322
    Prev
    Next
    INDEX
    Explanations

    Non-English texts

    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
    lav
    -0.08
    ditions
    -0.08
     sèche
    -0.08
    Ford
    -0.07
     набор
    -0.07
    redentials
    -0.07
    ucha
    -0.07
     разб
    -0.07
     apl
    -0.07
     ash
    -0.07
    POSITIVE LOGITS
    意义
    0.09
     sense
    0.08
     Sense
    0.08
     SHE
    0.08
     sentidos
    0.07
    吻
    0.07
    эконом
    0.07
    -wing
    0.07
     winger
    0.07
    広
    0.07
    Activations Density 0.015%

    No Known Activations