© 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. 71618
    Prev
    Next
    INDEX
    Explanations

    Shims and leveling

    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
     novelas
    -0.08
    laps
    -0.07
    生命周期
    -0.07
     cicl
    -0.07
     Ink
    -0.07
     prohib
    -0.07
     Symbols
    -0.07
     ejempl
    -0.07
    _symbols
    -0.07
     ©
    -0.07
    POSITIVE LOGITS
     reposition
    0.09
     pillows
    0.09
     verstel
    0.08
     cushioning
    0.08
    .Padding
    0.08
     mattress
    0.08
     fudge
    0.08
     mezi
    0.08
     piled
    0.08
     Fuji
    0.08
    Activations Density 0.016%

    No Known Activations