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. 54235
    Prev
    Next
    INDEX
    Explanations

    letters

    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
     Quebec
    -0.08
    λε
    -0.08
     qors
    -0.07
     Lung
    -0.07
     szerint
    -0.07
    quê
    -0.07
     adequ
    -0.07
     buil
    -0.07
     Lafayette
    -0.07
     Oregon
    -0.07
    POSITIVE LOGITS
    ẹwo
    0.08
    vonne
    0.08
    顔
    0.08
    esterday
    0.07
    仕事
    0.07
     rubbish
    0.07
     rainfall
    0.07
    earn
    0.07
     Hat
    0.07
    働
    0.07
    Activations Density 0.018%

    No Known Activations