© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 21974
    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
    ":↵↵
    -0.11
    �↵↵
    -0.10
    '):↵
    -0.09
    ':↵
    -0.09
    "):↵
    -0.09
    "]:↵
    -0.09
    ']):↵
    -0.09
    ":↵
    -0.08
    %的
    -0.08
     Here's
    -0.08
    POSITIVE LOGITS
     =
    0.14
     gives
    0.14
     =>
    0.13
    =
    0.13
     daje
    0.12
     them
    0.12
     yields
    0.12
     ->
    0.11
     equals
    0.10
     thereof
    0.10
    Activations Density 0.020%

    No Known Activations