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. 53140
    Prev
    Next
    INDEX
    Explanations

    through

    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
    806
    -0.08
    (The
    -0.07
     प्रत
    -0.07
     Eingang
    -0.07
    746
    -0.07
    234
    -0.07
    Fingerprint
    -0.07
    306
    -0.07
    arger
    -0.07
    374
    -0.07
    POSITIVE LOGITS
     smartwatch
    0.09
     pantalla
    0.09
     Hire
    0.08
     Vitória
    0.08
     viaj
    0.08
     divid
    0.08
     medier
    0.08
    decoded
    0.08
    уди
    0.08
     телев
    0.08
    Activations Density 0.012%

    No Known Activations