© 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. 21290
    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
     how
    -0.09
    (sorted
    -0.08
    (content
    -0.08
    ("[%
    -0.08
    ,"
    -0.08
     sorted
    -0.08
    (["
    -0.08
    (selection
    -0.08
     অভিন
    -0.08
    sorted
    -0.08
    POSITIVE LOGITS
    argv
    0.10
     argv
    0.09
    第二
    0.09
    =args
    0.09
    第
    0.08
    第三
    0.08
     втором
    0.08
     బాధ
    0.08
     vervol
    0.08
    כם
    0.08
    Activations Density 0.001%

    No Known Activations