Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 27225
    Prev
    Next
    INDEX
    Explanations

    numbers

    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
    Fiscal
    -0.09
     Fiscal
    -0.08
     llevaba
    -0.08
     fiscal
    -0.07
     ngayo
    -0.07
     Пров
    -0.07
     организа
    -0.07
     supposed
    -0.07
     Bellevue
    -0.07
     usuf
    -0.07
    POSITIVE LOGITS
     outre
    0.08
    servation
    0.08
     hairst
    0.08
     fris
    0.08
     lọ
    0.08
     outreach
    0.07
     옵션
    0.07
     אפשר
    0.07
    0.07
     verkauft
    0.07
    Activations Density 0.045%

    No Known Activations