© 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
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44589
    Prev
    Next
    INDEX
    Explanations

    code, revenue, french law

    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
    FAB
    -0.07
    ercise
    -0.07
    Module
    -0.07
    module
    -0.07
    fis
    -0.07
     Jaz
    -0.07
     module
    -0.07
    Poker
    -0.07
    Static
    -0.07
     geological
    -0.07
    POSITIVE LOGITS
     aml
    0.09
     uncanny
    0.09
     EACH
    0.08
    	except
    0.08
     élu
    0.08
    áne
    0.08
     Blond
    0.08
    叫什么
    0.08
    ancers
    0.08
     surprising
    0.08
    Activations Density 0.000%

    No Known Activations