© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 65458
    Prev
    Next
    INDEX
    Explanations

    javascript

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     noexcept
    -0.10
     therapists
    -0.09
     MDT
    -0.09
     CRT
    -0.09
     raken
    -0.09
    _completion
    -0.09
    pci
    -0.08
    packing
    -0.08
    declspec
    -0.08
    PCS
    -0.08
    POSITIVE LOGITS
     sails
    0.08
     Spreadsheet
    0.08
     luc
    0.08
     amo
    0.08
     Seychelles
    0.08
     Hive
    0.08
    .gs
    0.08
     enchant
    0.08
     Airt
    0.07
     lucid
    0.07
    Activations Density 0.007%

    No Known Activations