© 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. 19-RESID-POST-AA
    11. 103248
    Prev
    Next
    INDEX
    Explanations

    exercise and workouts

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restricciones
    -0.09
     nécess
    -0.09
     restrictions
    -0.08
     stringent
    -0.08
     a
    -0.08
     picturesque
    -0.08
     restrictive
    -0.08
     Entwicklungen
    -0.08
     ...
    -0.08
     erläut
    -0.07
    POSITIVE LOGITS
     упражнения
    0.14
    练
    0.13
     workouts
    0.12
     oefeningen
    0.12
     упраж
    0.12
     Sessions
    0.12
     journ
    0.12
     pratiquer
    0.12
     playlist
    0.12
     sessions
    0.11
    Activations Density 0.043%

    No Known Activations