© 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. 11-RESID-POST-AA
    11. 71661
    Prev
    Next
    INDEX
    Explanations

    of

    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
    Negative Logits
    изоля
    -0.09
    ечения
    -0.09
    _chunks
    -0.08
    itzer
    -0.08
    otherap
    -0.08
     prosec
    -0.08
    отеки
    -0.08
    ীদ
    -0.08
    разум
    -0.08
     берген
    -0.08
    POSITIVE LOGITS
     காலை
    0.17
     morning
    0.16
    晨
    0.16
     breakfast
    0.16
    早餐
    0.15
     सुबह
    0.15
    Morning
    0.15
     Breakfast
    0.14
    Breakfast
    0.13
     Morning
    0.13
    Activations Density 0.168%

    No Known Activations