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. 77428
    Prev
    Next
    INDEX
    Explanations

    chain

    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
     RUN
    -0.08
     kau
    -0.07
     गरी
    -0.07
     Flying
    -0.07
     المهمة
    -0.07
     అమ్మ
    -0.07
    -0.07
     Emilia
    -0.07
    elfth
    -0.07
     PRINT
    -0.07
    POSITIVE LOGITS
    webdriver
    0.08
    atil
    0.08
     soport
    0.08
     Sich
    0.07
    apat
    0.07
    ivial
    0.07
    agir
    0.07
     sweatshirt
    0.07
    velte
    0.07
     Sloven
    0.07
    Activations Density 0.001%

    No Known Activations