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. 112068
    Prev
    Next
    INDEX
    Explanations

    1

    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
    ोर
    -0.08
     mici
    -0.07
     commemorate
    -0.07
     સાથે
    -0.07
     रिकॉर्ड
    -0.07
     pope
    -0.07
     से
    -0.07
     مقدم
    -0.07
    처럼
    -0.07
    localized
    -0.07
    POSITIVE LOGITS
     relates
    0.07
     looks
    0.07
     tono
    0.07
     funct
    0.07
     picks
    0.07
     debug
    0.07
     Ea
    0.07
    'ha
    0.07
     riqueza
    0.07
     functionality
    0.07
    Activations Density 0.012%

    No Known Activations