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. 53055
    Prev
    Next
    INDEX
    Explanations

    enzymes and glycolysis

    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
     الوطنية
    -0.09
    announce
    -0.09
    开奖记录
    -0.09
    primitive
    -0.08
     الفنية
    -0.08
    prov
    -0.08
     aceste
    -0.08
     announce
    -0.08
     تلك
    -0.08
    elateerde
    -0.08
    POSITIVE LOGITS
     absorption
    0.08
    .Abs
    0.08
     fabs
    0.07
    價
    0.07
     kaç
    0.07
    abs
    0.07
    NB
    0.07
     ah
    0.07
    WM
    0.07
    態
    0.07
    Activations Density 0.001%

    No Known Activations