© 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. 11-RESID-POST-AA
    11. 63436
    Prev
    Next
    INDEX
    Explanations

    主

    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
    -Term
    -0.08
     Terrace
    -0.07
    退休
    -0.07
    Desired
    -0.07
    Vi
    -0.07
    'image
    -0.07
     conclusion
    -0.07
     визу
    -0.07
    -painted
    -0.07
    毕业
    -0.07
    POSITIVE LOGITS
     host
    0.14
    Host
    0.12
     Host
    0.12
    host
    0.12
    _host
    0.12
    .host
    0.12
    	host
    0.11
    (host
    0.11
    _HOST
    0.11
     anfit
    0.10
    Activations Density 0.005%

    No Known Activations