© 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. 45280
    Prev
    Next
    INDEX
    Explanations

    scroll behavior smooth

    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
     stamped
    -0.08
     parano
    -0.08
    _UNUSED
    -0.08
     synopsis
    -0.08
     flamb
    -0.08
     diplom
    -0.08
     zool
    -0.08
     allá
    -0.07
     anthropology
    -0.07
     abuses
    -0.07
    POSITIVE LOGITS
     fondos
    0.08
     scrolling
    0.08
     गति
    0.08
     automatically
    0.08
     estabilidad
    0.08
     precipitation
    0.08
     automatiquement
    0.08
     precisión
    0.07
     soften
    0.07
     stabilité
    0.07
    Activations Density 0.002%

    No Known Activations