© 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. 110063
    Prev
    Next
    INDEX
    Explanations

    Tap

    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
    лага
    -0.09
     teeth
    -0.09
    bid
    -0.08
    ald
    -0.07
     मै
    -0.07
     enkel
    -0.07
     tempered
    -0.07
     Einst
    -0.07
     Cook
    -0.07
     Toby
    -0.07
    POSITIVE LOGITS
     Nadu
    0.08
    poral
    0.07
     glimpse
    0.07
    0.07
    เติม
    0.07
    摘
    0.07
    worthy
    0.07
    ویزی
    0.07
    射
    0.07
    촉
    0.07
    Activations Density 0.005%
    No Known Activations