© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 47973
    Prev
    Next
    INDEX
    Explanations

    fitness

    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
    出票
    -0.10
     lluvia
    -0.10
    外交
    -0.10
     дипломат
    -0.10
     Magistr
    -0.09
     Nobel
    -0.09
     Bürger
    -0.09
     আদাল
    -0.09
     વરસાદ
    -0.09
     diplomats
    -0.09
    POSITIVE LOGITS
     fitness
    0.35
     workout
    0.34
     bodybuilding
    0.34
     Fitness
    0.33
    Fitness
    0.33
     фит
    0.32
    fitness
    0.31
    Workout
    0.31
     workouts
    0.31
     Workout
    0.30
    Activations Density 0.105%

    No Known Activations