© 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 EvalsExportsAPI 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. 20215
    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
     rup
    -0.08
     beleza
    -0.08
     ಮೇಲೆ
    -0.08
    ließen
    -0.08
     כתב
    -0.08
    sgesamt
    -0.08
    wụ
    -0.07
     ಉತ್ತ
    -0.07
     welchem
    -0.07
     trắng
    -0.07
    POSITIVE LOGITS
     خانو
    0.09
    (use
    0.08
     usar
    0.08
     पार्क
    0.08
    occupied
    0.07
     käyttää
    0.07
     परिवार
    0.07
    meni
    0.07
     usare
    0.07
     οικο
    0.07
    Activations Density 0.000%

    No Known Activations