© 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. 109994
    Prev
    Next
    INDEX
    Explanations

    supervision

    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
     Fitzgerald
    -0.08
    �
    -0.08
    wine
    -0.07
    sep
    -0.07
    assat
    -0.07
     depres
    -0.07
    QC
    -0.07
     Breit
    -0.07
     MCA
    -0.07
     Had
    -0.07
    POSITIVE LOGITS
    Encounter
    0.07
     crack
    0.07
    ите
    0.07
     impart
    0.07
    意见
    0.07
    िला
    0.07
     tangible
    0.07
     नाव
    0.06
     پیش
    0.06
    ിത
    0.06
    Activations Density 0.005%

    No Known Activations