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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 45009
    Prev
    Next
    INDEX
    Explanations

    English

    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
     quotid
    -0.08
     न्याय
    -0.07
     предп
    -0.07
     justice
    -0.07
     Ha
    -0.07
     fals
    -0.07
     Hermann
    -0.07
    mens
    -0.07
     manifest
    -0.07
     Armen
    -0.07
    POSITIVE LOGITS
    百科
    0.10
    -air
    0.09
     encyclopedia
    0.08
    ’ind
    0.08
     atleast
    0.08
    Wikipedia
    0.08
     masterpiece
    0.08
    ільки
    0.08
     monop
    0.08
    vänd
    0.08
    Activations Density 0.000%

    No Known Activations