© 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. 30062
    Prev
    Next
    INDEX
    Explanations

    comma

    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
    永久
    -0.09
     diets
    -0.08
     holy
    -0.08
    未来
    -0.07
    时代
    -0.07
    -disciplinary
    -0.07
     për
    -0.07
     Shed
    -0.07
     associated
    -0.07
     responsabilidades
    -0.07
    POSITIVE LOGITS
     сустав
    0.11
     вращ
    0.11
     груз
    0.10
     позвоноч
    0.09
     қыз
    0.08
     Chicken
    0.08
     гим
    0.08
     постепенно
    0.08
     Triangle
    0.08
     мах
    0.08
    Activations Density 0.004%

    No Known Activations