© 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 EvalsExportsAPI 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. 20264
    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
     subtree
    -0.10
    <Tree
    -0.09
    (tree
    -0.09
    χος
    -0.09
    <Base
    -0.09
    (Tree
    -0.09
    (Xml
    -0.09
     surfer
    -0.08
    ’entre
    -0.08
    (xml
    -0.08
    POSITIVE LOGITS
     crumble
    0.11
     feta
    0.10
    碎
    0.10
     revoke
    0.09
     enclave
    0.09
     crumb
    0.09
     grams
    0.09
    破
    0.09
     apartamento
    0.09
    mailto
    0.09
    Activations Density 0.006%

    No Known Activations