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

    Neuronpedia

    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. 11-RESID-POST-AA
    11. 54316
    Prev
    Next
    INDEX
    Explanations

    programming code

    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
     reviewing
    -0.08
     시장
    -0.08
    시장
    -0.07
     wirtschaft
    -0.07
    uating
    -0.07
     market
    -0.07
    appid
    -0.07
     Reviewing
    -0.07
    scripts
    -0.07
     upl
    -0.07
    POSITIVE LOGITS
     recursively
    0.17
    递
    0.15
     recursion
    0.14
    Recursive
    0.14
    _recursive
    0.14
     recursive
    0.14
     recurse
    0.14
     Recursive
    0.13
    recursive
    0.12
     réc
    0.11
    Activations Density 0.009%

    No Known Activations