© 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. 30081
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     necesita
    -0.08
    ходим
    -0.08
    antai
    -0.08
     Belt
    -0.07
    ptăm
    -0.07
     seemingly
    -0.07
    -0.07
    ldə
    -0.07
     antibiotic
    -0.07
    售价
    -0.07
    POSITIVE LOGITS
     lar
    0.08
     Kam
    0.08
    Kam
    0.08
     Hist
    0.07
     तौर
    0.07
    oper
    0.07
     läbi
    0.07
     यही
    0.07
     lên
    0.07
    Hy
    0.07
    Activations Density 0.124%
    No Known Activations