© 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. 51064
    Prev
    Next
    INDEX
    Explanations

    �

    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
     ngo
    -0.07
    .ass
    -0.07
     chores
    -0.07
     begeleiden
    -0.07
    ay
    -0.07
     മാറ
    -0.07
     assoc
    -0.07
    -0.07
    кое
    -0.07
    (K
    -0.07
    POSITIVE LOGITS
     న
    0.08
     ప్రత
    0.08
    ულ
    0.07
    rog
    0.07
     Gilbert
    0.07
     ఆశ
    0.07
    uchs
    0.07
     спокойно
    0.07
    ప్ర
    0.07
    ਡੀ
    0.07
    Activations Density 0.000%
    No Known Activations