© 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. 17981
    Prev
    Next
    INDEX
    Explanations

    sandwiches

    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
     astrolog
    -0.11
    Quaternion
    -0.10
     astrology
    -0.10
     Kinect
    -0.10
    	camera
    -0.10
    RGCTXData
    -0.10
     Draco
    -0.10
    .rpc
    -0.09
    .JSONObject
    -0.09
     చంద్ర
    -0.09
    POSITIVE LOGITS
     sandwiches
    0.19
     sandwich
    0.19
     Sandwich
    0.18
     bread
    0.18
     pão
    0.16
     breads
    0.16
     burger
    0.14
     хлеб
    0.14
     deli
    0.14
     toaster
    0.14
    Activations Density 0.021%

    No Known Activations