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. 78547
    Prev
    Next
    INDEX
    Explanations

    cable types

    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
     flujo
    -0.10
     fluxo
    -0.09
     Flux
    -0.09
     flow
    -0.08
    flow
    -0.08
     DAO
    -0.08
    .vaadin
    -0.08
    workflow
    -0.07
     javafx
    -0.07
     حکومت
    -0.07
    POSITIVE LOGITS
    Wireless
    0.09
    acebook
    0.08
    bestos
    0.08
    azzi
    0.08
    ارع
    0.08
    chent
    0.08
     artik
    0.08
    Bell
    0.08
     unplug
    0.08
     uz
    0.08
    Activations Density 0.003%

    No Known Activations