© 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. 99230
    Prev
    Next
    INDEX
    Explanations

    ground

    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
     wasn
    -0.08
    ']}
    -0.08
     llegó
    -0.08
     cá
    -0.08
     wasn't
    -0.07
    ящий
    -0.07
    ятель
    -0.07
     получится
    -0.07
     Winter
    -0.07
     bagus
    -0.07
    POSITIVE LOGITS
     πλευ
    0.09
     સિવ
    0.08
     земле
    0.08
     oncology
    0.07
    ροσ
    0.07
     наз
    0.07
     scoring
    0.07
    側
    0.07
    ște
    0.07
     फोन
    0.07
    Activations Density 0.006%

    No Known Activations