© 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. 71773
    Prev
    Next
    INDEX
    Explanations

    AI explainability

    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
     skier
    -0.08
    _tbl
    -0.08
    Paste
    -0.08
     renewal
    -0.08
     Countdown
    -0.08
     Woodstock
    -0.07
    ター
    -0.07
     flawless
    -0.07
     Slee
    -0.07
    Recycle
    -0.07
    POSITIVE LOGITS
     pruning
    0.12
     interpret
    0.10
     heur
    0.10
     neuron
    0.10
     interpre
    0.10
    Visualization
    0.09
     prune
    0.09
     visualization
    0.09
     nachvoll
    0.09
     Visualization
    0.09
    Activations Density 0.005%

    No Known Activations