© 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. 110092
    Prev
    Next
    INDEX
    Explanations

    numbers and digits

    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
     journal
    -0.08
    餐
    -0.08
     Buddy
    -0.08
     EA
    -0.08
     రోజుల
    -0.08
     Objective
    -0.08
     jurnal
    -0.08
    ,Unity
    -0.07
     keç
    -0.07
    技巧
    -0.07
    POSITIVE LOGITS
     표시
    0.09
    pron
    0.08
     Yorkers
    0.08
     standby
    0.08
     breakdown
    0.07
     firefighters
    0.07
    ่ว
    0.07
    crow
    0.07
    Placement
    0.07
    YOffset
    0.07
    Activations Density 0.017%

    No Known Activations