© 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. 19538
    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
     কিংবা
    -0.10
     or
    -0.09
    或者
    -0.09
     किंवा
    -0.09
     অথবা
    -0.09
     അല്ല
    -0.09
     וגם
    -0.09
     ataupun
    -0.09
     বা
    -0.09
     અથવા
    -0.09
    POSITIVE LOGITS
    1
    0.11
    app
    0.09
    any
    0.09
    ）↵↵
    0.08
     الأولى
    0.08
    acting
    0.08
     any
    0.08
    0.08
    estros
    0.07
    agi
    0.07
    Activations Density 0.001%
    No Known Activations