© 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. 43556
    Prev
    Next
    INDEX
    Explanations

    Minimum viable product

    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
     verb
    -0.07
    MAIN
    -0.07
    lex
    -0.07
    PILE
    -0.07
    IDAY
    -0.07
    .strict
    -0.07
    ummary
    -0.07
    	source
    -0.07
    verb
    -0.07
    >Main
    -0.07
    POSITIVE LOGITS
     technically
    0.09
     innov
    0.08
     innovate
    0.08
     practically
    0.08
     بودن
    0.08
     powders
    0.08
     продукта
    0.07
     tolerated
    0.07
     logistics
    0.07
     �
    0.07
    Activations Density 0.001%

    No Known Activations