© 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. 23-RESID-POST-AA
    11. 50190
    Prev
    Next
    INDEX
    Explanations

    say "android"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Width
    -0.10
    .Width
    -0.10
    ?r
    -0.10
    _width
    -0.09
    /Grid
    -0.09
    ">{
    -0.09
    /text
    -0.09
    _size
    -0.09
    _title
    -0.09
    Title
    -0.09
    POSITIVE LOGITS
     process
    0.09
     export
    0.08
    Factories
    0.08
    (process
    0.08
     extract
    0.08
     destroy
    0.08
     destroyed
    0.08
     exported
    0.08
     spawn
    0.08
    èces
    0.08
    Activations Density 0.001%

    No Known Activations