© 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. 23-RESID-POST-AA
    11. 47893
    Prev
    Next
    INDEX
    Explanations

    say "یس"

    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
    udio
    -0.08
    ovirus
    -0.08
     ov
    -0.08
     orang
    -0.08
    ov
    -0.08
    Ol
    -0.08
     resting
    -0.08
    ovir
    -0.07
     OV
    -0.07
     adaptable
    -0.07
    POSITIVE LOGITS
     whisky
    0.08
     dehydr
    0.08
     pinch
    0.08
    twitter
    0.08
    ticket
    0.08
    standen
    0.07
     haze
    0.07
    	std
    0.07
     dobb
    0.07
    ‍ക്കും
    0.07
    Activations Density 0.000%

    No Known Activations