© 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. 21921
    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
    २०७
    -0.12
     තිය
    -0.11
     הזאת
    -0.11
     entonces
    -0.10
     ცვლილ
    -0.10
     qinn
    -0.10
    annalu
    -0.10
     הזו
    -0.10
    ८
    -0.10
    偷拍自拍
    -0.10
    POSITIVE LOGITS
    ly
    0.10
     frontier
    0.10
     efficient
    0.09
     impact
    0.08
     eficiente
    0.08
     효
    0.08
     Frontier
    0.08
    -efficient
    0.08
     eficientes
    0.08
     effiz
    0.08
    Activations Density 0.012%

    No Known Activations