© 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. 19-RESID-POST-AA
    11. 21618
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     πή
    -0.08
    ၄
    -0.08
    ၆
    -0.08
    uneka
    -0.08
     şeyi
    -0.08
     vierde
    -0.08
    örder
    -0.08
    akash
    -0.08
     وکړه
    -0.08
    四
    -0.08
    POSITIVE LOGITS
    guards
    0.11
    guard
    0.10
    plan
    0.10
     mass
    0.10
    mass
    0.09
    -parser
    0.09
    yards
    0.09
    builder
    0.09
     సమస్య
    0.09
     masalah
    0.08
    Activations Density 0.015%

    No Known Activations