© 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. 96189
    Prev
    Next
    INDEX
    Explanations

    Forms of "exercise"

    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
    uplicate
    -0.08
     ajudar
    -0.08
     ermöglichen
    -0.08
     помочь
    -0.08
    ившись
    -0.08
     aiut
    -0.08
     liefern
    -0.08
     ajud
    -0.08
     produjo
    -0.08
     assistance
    -0.08
    POSITIVE LOGITS
     exercise
    0.24
     exercises
    0.23
     exercising
    0.23
     Exercise
    0.22
     Exercises
    0.21
    Exercise
    0.21
     eserc
    0.21
    exercise
    0.21
     exercer
    0.21
     exerce
    0.21
    Activations Density 0.059%

    No Known Activations