© 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. 23-RESID-POST-AA
    11. 51133
    Prev
    Next
    INDEX
    Explanations

    body modification

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cleanser
    -0.08
     shaking
    -0.08
    谢
    -0.08
    allax
    -0.08
     gates
    -0.08
     shake
    -0.08
     shred
    -0.07
    (Debug
    -0.07
     drafting
    -0.07
     Shake
    -0.07
    POSITIVE LOGITS
     implants
    0.17
     implanted
    0.16
     implantation
    0.15
     prost
    0.15
     modifications
    0.15
     implant
    0.15
     augment
    0.14
     modificaciones
    0.14
    implant
    0.14
    _impl
    0.14
    Activations Density 0.073%

    No Known Activations