© 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. 22136
    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
     orice
    -0.09
    ','=
    -0.09
     wordt
    -0.08
     любое
    -0.08
     कोई
    -0.08
     степень
    -0.08
     mult
    -0.08
     jopa
    -0.08
     możliwość
    -0.07
     ಯಾವುದೇ
    -0.07
    POSITIVE LOGITS
     của
    0.10
     لـ
    0.10
    (St
    0.10
    :**
    0.09
     עבור
    0.09
    /St
    0.09
     های
    0.09
     ของ
    0.09
    -material
    0.09
     ntawm
    0.09
    Activations Density 0.072%

    No Known Activations