© 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. 18126
    Prev
    Next
    INDEX
    Explanations

    bin

    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
     తెరక
    -0.13
    יישאַן
    -0.12
    公众号天天中彩票
    -0.12
    -nyň
    -0.12
     全民彩票天天送
    -0.12
     天天彩票是
    -0.12
     天天中彩票公众号
    -0.12
    -国产
    -0.12
    лиқиниң
    -0.12
    -0.12
    POSITIVE LOGITS
    _{
    0.16
    !(
    0.12
    _k
    0.12
    }(
    0.12
    _(
    0.12
    _coeff
    0.12
    _n
    0.11
    /(
    0.11
    _i
    0.11
    _sum
    0.11
    Activations Density 0.008%
    No Known Activations