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. 12977
    Prev
    Next
    INDEX
    Explanations

    4

    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
    -minded
    -0.08
     scrib
    -0.07
    �
    -0.07
     REP
    -0.07
     brook
    -0.07
     tir
    -0.07
    lace
    -0.07
     reizen
    -0.06
    」↵
    -0.06
     vain
    -0.06
    POSITIVE LOGITS
     Eurovision
    0.09
     efectivo
    0.08
    ево
    0.08
     publico
    0.08
     empirical
    0.08
     empir
    0.08
     cheesecake
    0.07
    ovi
    0.07
    yeed
    0.07
     Rockefeller
    0.07
    Activations Density 0.049%

    No Known Activations