© 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. 71796
    Prev
    Next
    INDEX
    Explanations

    bermudagrass

    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
     usa
    -0.08
    小说
    -0.07
     JSONObject
    -0.07
    Animator
    -0.07
    urtle
    -0.07
     Magical
    -0.07
     JSON
    -0.07
    -0.07
     Potion
    -0.07
    JSON
    -0.07
    POSITIVE LOGITS
    grass
    0.12
     grasses
    0.11
     rye
    0.10
     weeds
    0.09
    禾
    0.09
     pasture
    0.09
     grass
    0.09
     grout
    0.09
    -soft
    0.09
     meadow
    0.09
    Activations Density 0.008%
    No Known Activations