© 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 EvalsExportsinterp-engineNEWAPI 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. 110818
    Prev
    Next
    INDEX
    Explanations

    chemistry, oxygen, spanish

    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
     nú
    -0.09
     carbón
    -0.08
     llevará
    -0.07
    年度
    -0.07
     ظل
    -0.07
    .deepcopy
    -0.07
     shelf
    -0.07
     viene
    -0.07
     delinc
    -0.07
     körper
    -0.07
    POSITIVE LOGITS
    Inclusive
    0.08
    including
    0.08
    ீர்
    0.08
     সম্পর্কে
    0.08
    orn
    0.08
    fore
    0.08
     +-
    0.08
     inkluder
    0.07
    soo
    0.07
     dito
    0.07
    Activations Density 0.000%

    No Known Activations