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. 7-RESID-POST-AA
    6. 130974
    Prev
    Next
    INDEX
    Explanations

    guard

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    پو
    -0.08
    stash
    -0.07
    mins
    -0.07
    م
    -0.07
    纵
    -0.07
     Heel
    -0.07
    关键词
    -0.07
    rev
    -0.07
     presentar
    -0.07
    rush
    -0.07
    POSITIVE LOGITS
     لق
    0.09
     сиз
    0.08
     GI
    0.08
    Ukraine
    0.07
     child's
    0.07
     Dragon
    0.07
     gram
    0.07
     acted
    0.07
     ouvertes
    0.07
     Prints
    0.07
    Activations Density 0.001%

    No Known Activations