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. 49228
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     reacting
    -0.08
     important
    -0.08
    主体
    -0.08
     wrongdoing
    -0.07
    entries
    -0.07
    、それ
    -0.07
     ধর
    -0.07
     hook
    -0.07
     having
    -0.07
    连
    -0.07
    POSITIVE LOGITS
     Polska
    0.09
     기타
    0.09
     Gastro
    0.08
    롯
    0.08
     Spanien
    0.08
     sele
    0.08
     은
    0.08
    ök
    0.08
     terl
    0.07
    .foundation
    0.07
    Activations Density 0.034%

    No Known Activations