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. 30570
    Prev
    Next
    INDEX
    Explanations

    sure

    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
    ixe
    -0.08
     inns
    -0.08
     clas
    -0.08
     oxid
    -0.08
    pant
    -0.07
     insgesamt
    -0.07
    appear
    -0.07
    acken
    -0.07
     Sut
    -0.07
    CP
    -0.07
    POSITIVE LOGITS
     rằng
    0.10
     Hawkins
    0.08
     enough
    0.08
    是不是
    0.08
    ว่
    0.08
    GEST
    0.08
     بشأن
    0.07
     πως
    0.07
    是哪
    0.07
    hag
    0.07
    Activations Density 0.033%

    No Known Activations