© 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. 18007
    Prev
    Next
    INDEX
    Explanations

    **

    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
    、『
    -0.08
    admins
    -0.08
    、中
    -0.08
    Encrypt
    -0.08
    .Use
    -0.08
    _use
    -0.08
    -invalid
    -0.07
    -pin
    -0.07
    、日本
    -0.07
    -bank
    -0.07
    POSITIVE LOGITS
     (
    0.14
    （
    0.11
     （
    0.11
     anschließend
    0.09
    そして
    0.09
     daarnaast
    0.09
     valamint
    0.09
    (
    0.09
    aution
    0.09
    /oder
    0.09
    Activations Density 0.083%

    No Known Activations