© 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. 64000
    Prev
    Next
    INDEX
    Explanations

    website terms/disclaimers

    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
    .dumps
    -0.09
     удалось
    -0.09
    tones
    -0.09
    needed
    -0.08
     Surprisingly
    -0.08
     고민
    -0.08
     gardeners
    -0.08
    OUGH
    -0.08
     nursing
    -0.08
    urgy
    -0.08
    POSITIVE LOGITS
    免责声明
    0.15
     Disclaimer
    0.13
    免责
    0.13
     disclaimer
    0.13
     copyrighted
    0.12
     liability
    0.12
     hereby
    0.11
     copyright
    0.11
     Liability
    0.11
     indemn
    0.11
    Activations Density 0.157%

    No Known Activations