© 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. 19-RESID-POST-AA
    11. 18182
    Prev
    Next
    INDEX
    Explanations

    say "time period"

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    uelta
    -0.08
    లు
    -0.08
    ాలు
    -0.08
    owered
    -0.07
    mals
    -0.07
    ो
    -0.07
     Supporting
    -0.07
    -0.07
     {},↵
    -0.07
     поддерж
    -0.07
    POSITIVE LOGITS
     year's
    0.23
     day's
    0.22
     month's
    0.21
     country's
    0.21
     week's
    0.21
     city's
    0.20
     company's
    0.20
     night's
    0.20
    年的
    0.19
     ವರ್ಷದ
    0.18
    Activations Density 0.029%
    No Known Activations