© 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. 22073
    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
    들은
    -0.10
    들의
    -0.09
    들도
    -0.08
    /etc
    -0.07
    Kalaallit
    -0.07
    enames
    -0.07
    हरूले
    -0.07
     অধিক
    -0.07
     equivalents
    -0.07
     назы
    -0.07
    POSITIVE LOGITS
    (index
    0.08
     versi
    0.08
     marcador
    0.08
     또
    0.08
    ถึง
    0.08
     predefined
    0.08
    (common
    0.08
    (local
    0.08
    another
    0.07
     then
    0.07
    Activations Density 0.037%

    No Known Activations