© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 51953
    Prev
    Next
    INDEX
    Explanations

    餐

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    names
    -0.08
    -0.08
    ppers
    -0.08
    prav
    -0.08
    ctions
    -0.08
    omers
    -0.08
    itters
    -0.07
     раздел
    -0.07
    ucao
    -0.07
    issons
    -0.07
    POSITIVE LOGITS
    厅
    0.20
    饮
    0.17
    馆
    0.17
    館
    0.14
    具
    0.13
    飲
    0.13
    桌
    0.12
    点
    0.11
    點
    0.10
     drink
    0.10
    Activations Density 0.003%
    No Known Activations