© 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. 109929
    Prev
    Next
    INDEX
    Explanations

    ier/cabinet

    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
    -0.08
    concept
    -0.07
    .includes
    -0.07
    .jpg
    -0.07
     escalate
    -0.07
     concept
    -0.07
    .cert
    -0.07
    Annotated
    -0.07
    ại
    -0.07
     parking
    -0.07
    POSITIVE LOGITS
     piir
    0.09
     απ
    0.09
     Heck
    0.09
    _RENDER
    0.08
    准
    0.08
     шк
    0.08
     Halb
    0.08
     slit
    0.08
     бер
    0.08
    ämp
    0.08
    Activations Density 0.001%
    No Known Activations