© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44498
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical writing & language mix

    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
    fiction
    -0.09
     wildcard
    -0.08
     Whisper
    -0.08
     Wik
    -0.08
     Grammarly
    -0.08
    .Audio
    -0.08
     plural
    -0.07
     spree
    -0.07
    hunt
    -0.07
     Fiction
    -0.07
    POSITIVE LOGITS
     endothelial
    0.13
     adhesion
    0.12
     dysfunction
    0.10
     attractiveness
    0.09
     permeability
    0.09
    _HEADERS
    0.09
     aantrekkelijk
    0.08
     vascular
    0.08
     aantrekk
    0.08
     podia
    0.08
    Activations Density 0.004%

    No Known Activations