© 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. 109823
    Prev
    Next
    INDEX
    Explanations

    luxury

    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
    Shar
    -0.09
    Pun
    -0.08
     Issue
    -0.07
     خلک
    -0.07
     Markle
    -0.07
     Shar
    -0.07
     TOT
    -0.07
    Stake
    -0.07
     Praise
    -0.07
     grave
    -0.07
    POSITIVE LOGITS
    典
    0.09
    主义
    0.08
    理念
    0.08
    成果
    0.08
     continental
    0.08
     અનુભ
    0.08
    しい
    0.08
    तम
    0.07
     trafficking
    0.07
    雅
    0.07
    Activations Density 0.006%

    No Known Activations