© 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. 11-RESID-POST-AA
    11. 26529
    Prev
    Next
    INDEX
    Explanations

    trains and speed

    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
     ){↵
    -0.08
     mantener
    -0.08
     ){↵↵
    -0.08
     recreation
    -0.08
     maint
    -0.07
     recreate
    -0.07
    维
    -0.07
    شو
    -0.07
     maintenir
    -0.07
     llenar
    -0.07
    POSITIVE LOGITS
     скорости
    0.11
     speeds
    0.11
     velocidades
    0.10
     سرعة
    0.10
     velocidade
    0.10
     скорость
    0.10
    _SPEED
    0.10
     faster
    0.09
     airborne
    0.09
    _speed
    0.09
    Activations Density 0.013%

    No Known Activations