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. 60901
    Prev
    Next
    INDEX
    Explanations

    type

    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
    었
    -0.08
    Bodies
    -0.08
    _OPTIONS
    -0.08
     annunci
    -0.08
    .messaging
    -0.08
    ด้วย
    -0.08
     messaging
    -0.08
     FEMA
    -0.08
     investigators
    -0.07
    奉
    -0.07
    POSITIVE LOGITS
     crispy
    0.08
     sinc
    0.08
    ład
    0.08
     dragon
    0.08
     stove
    0.08
    ffs
    0.07
     ultra
    0.07
     technology
    0.07
     ouro
    0.07
    оң
    0.07
    Activations Density 0.002%

    No Known Activations