© 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. 71657
    Prev
    Next
    INDEX
    Explanations

    Roman history

    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
    Shadow
    -0.08
    _shadow
    -0.08
    Detached
    -0.08
     Shadow
    -0.08
     shadow
    -0.08
     enzymes
    -0.08
     OLED
    -0.08
    shadow
    -0.08
     Dong
    -0.08
    前年比
    -0.08
    POSITIVE LOGITS
     romano
    0.09
     Roman
    0.09
     romana
    0.08
     rigtig
    0.08
     NFL
    0.08
     roman
    0.07
    Roman
    0.07
     amerik
    0.07
     FBI
    0.07
     jean
    0.07
    Activations Density 0.019%

    No Known Activations