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. 130457
    Prev
    Next
    INDEX
    Explanations

    computer networking

    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
    Park
    -0.08
    roof
    -0.08
     Pele
    -0.08
     scar
    -0.08
     Recreation
    -0.07
     �
    -0.07
     totalidad
    -0.07
     viet
    -0.07
     vulgar
    -0.07
     redevelopment
    -0.07
    POSITIVE LOGITS
    -routing
    0.11
    .navigate
    0.10
     Routing
    0.10
     маршру
    0.10
    (routes
    0.10
    .routing
    0.09
     வித
    0.09
     routing
    0.09
    Routing
    0.09
    routing
    0.09
    Activations Density 0.006%

    No Known Activations