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. 113030
    Prev
    Next
    INDEX
    Explanations

    indices of math/code

    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
    울
    -0.08
     쓰
    -0.08
     offres
    -0.08
     钱
    -0.08
    τέρα
    -0.08
     외
    -0.08
    Tür
    -0.08
     lacag
    -0.08
    omar
    -0.08
     줄
    -0.08
    POSITIVE LOGITS
     cambio
    0.08
     pequeño
    0.08
    答
    0.08
     Burgundy
    0.07
     Cartesian
    0.07
     estratégico
    0.07
     صغير
    0.07
     manor
    0.07
     grandson
    0.07
     cultivo
    0.07
    Activations Density 0.066%

    No Known Activations