© 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. 99893
    Prev
    Next
    INDEX
    Explanations

    warming up before exercise

    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
     embro
    -0.08
     aprovech
    -0.08
     bubbles
    -0.08
     пузыр
    -0.08
    消费
    -0.07
    宗
    -0.07
     eccles
    -0.07
     médicament
    -0.07
     inscription
    -0.07
     matrimon
    -0.07
    POSITIVE LOGITS
     warm
    0.09
    .Header
    0.09
     항상
    0.09
     Workout
    0.09
     ورزش
    0.09
     चोट
    0.09
     warming
    0.09
     blessures
    0.09
     לפני
    0.09
     precautions
    0.08
    Activations Density 0.008%

    No Known Activations