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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11769
    Prev
    Next
    INDEX
    Explanations

    Employer Identification Number (EIN)

    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
     interloc
    -0.08
     Shore
    -0.08
     optimal
    -0.08
     safe
    -0.07
     cerrar
    -0.07
     fortalecer
    -0.07
     handen
    -0.07
     Indones
    -0.07
    -0.07
     ejercer
    -0.07
    POSITIVE LOGITS
     бизнес
    0.08
    rm
    0.08
    kend
    0.08
     Кос
    0.08
     고
    0.07
     ARN
    0.07
     COS
    0.07
    ڙ
    0.07
     Rats
    0.07
     диаб
    0.07
    Activations Density 0.004%

    No Known Activations