© 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. 110193
    Prev
    Next
    INDEX
    Explanations

    DNA base pairs

    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
     Shape
    -0.07
    Shape
    -0.07
     Zustand
    -0.07
     през
    -0.07
    Dismiss
    -0.07
     shape
    -0.07
     saha
    -0.07
    ilan
    -0.07
    确认
    -0.07
    确定
    -0.07
    POSITIVE LOGITS
     percentile
    0.10
     درصد
    0.10
     শতাংশ
    0.10
     percentual
    0.10
     Prozent
    0.09
    percent
    0.09
    _percent
    0.09
     procent
    0.09
    _PERCENT
    0.09
    Percentage
    0.09
    Activations Density 0.003%

    No Known Activations