© 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. 22093
    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
     diğer
    -0.09
     vérit
    -0.08
     First
    -0.08
     سایر
    -0.08
     %(
    -0.08
     همچنین
    -0.08
     øvr
    -0.08
     andere
    -0.08
     %
    -0.07
    -0.07
    POSITIVE LOGITS
     какого
    0.14
     regarding
    0.12
     asking
    0.12
    ?↵
    0.12
     urgently
    0.12
     прось
    0.12
    ?↵↵
    0.11
    ?↵↵↵↵
    0.11
     какую
    0.11
     مني
    0.11
    Activations Density 0.057%

    No Known Activations