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. 77447
    Prev
    Next
    INDEX
    Explanations

    numerical formulas

    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
     pares
    -0.09
     push
    -0.08
     tuition
    -0.08
    push
    -0.07
     multiplex
    -0.07
     أج
    -0.07
     confirmer
    -0.07
     Roman
    -0.07
     ملت
    -0.07
     city
    -0.07
    POSITIVE LOGITS
     Avoid
    0.12
     предотвращ
    0.11
     precautions
    0.11
    Avoid
    0.11
    避免
    0.10
     избег
    0.10
     safeguards
    0.10
     evita
    0.10
     avoid
    0.10
     safegu
    0.10
    Activations Density 0.004%

    No Known Activations