© 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. 71345
    Prev
    Next
    INDEX
    Explanations

    meat

    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
     Howell
    -0.09
     chalk
    -0.09
    66
    -0.07
     Nicole
    -0.07
     sticky
    -0.07
    -worthy
    -0.07
     capacitor
    -0.07
     Ka
    -0.07
     meis
    -0.07
     Melo
    -0.07
    POSITIVE LOGITS
     Drop
    0.08
     육
    0.08
     ethic
    0.08
    สัต
    0.07
    류
    0.07
    Linha
    0.07
    طع
    0.07
    Bone
    0.07
    stück
    0.07
    انی
    0.07
    Activations Density 0.010%

    No Known Activations