© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 70972
    Prev
    Next
    INDEX
    Explanations

    catalytic

    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
    Not in Any Lists

    No Comments

    Negative Logits
     amateur
    -0.10
     endorsed
    -0.09
     hacked
    -0.09
     sham
    -0.09
     emot
    -0.09
     romantic
    -0.09
     fundraising
    -0.08
     funded
    -0.08
     faint
    -0.08
     beat
    -0.08
    POSITIVE LOGITS
     refinery
    0.09
     pellets
    0.08
     Docker
    0.08
     coke
    0.08
    kie
    0.08
    Magento
    0.08
    Docker
    0.07
     upgrading
    0.07
    docker
    0.07
     sulfur
    0.07
    Activations Density 0.003%

    No Known Activations