© 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. 21796
    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
    ,↵
    -0.08
     gunakan
    -0.08
     or
    -0.08
     bruker
    -0.07
     to
    -0.07
     utilisez
    -0.07
    ,↵↵
    -0.07
     nom
    -0.07
    fant
    -0.07
     नाम
    -0.07
    POSITIVE LOGITS
     clarification
    0.12
    是在
    0.12
     clarified
    0.12
     clearer
    0.12
     rằng
    0.12
     bahawa
    0.11
     waarschijnlijk
    0.11
     likely
    0.11
    就是说
    0.11
    詳細
    0.11
    Activations Density 0.012%

    No Known Activations