© 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. 22611
    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
    ացել
    -0.09
    ႐
    -0.09
     miliyoni
    -0.09
    %"
    -0.09
     Бога
    -0.09
     <>",
    -0.09
    ҳур
    -0.09
    արգել
    -0.08
    անալու
    -0.08
    ()->
    -0.08
    POSITIVE LOGITS
    orithm
    0.10
     Idea
    0.09
    orem
    0.09
     Assertion
    0.09
     Implementation
    0.09
     Step
    0.09
     Section
    0.09
     Schritt
    0.08
     Claim
    0.08
     Example
    0.08
    Activations Density 0.005%

    No Known Activations