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. 53297
    Prev
    Next
    INDEX
    Explanations

    liability

    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
     дър
    -0.08
     beating
    -0.08
     Bootstrap
    -0.08
     cheating
    -0.08
     ferry
    -0.07
    Bootstrap
    -0.07
     жив
    -0.07
     GOVERN
    -0.07
    -0.07
     Clas
    -0.07
    POSITIVE LOGITS
     verursacht
    0.10
    Ihre
    0.08
     alleging
    0.08
     veroorzaakt
    0.08
     erhö
    0.08
    ensure
    0.08
    issan
    0.08
    .clean
    0.08
    entlich
    0.08
     lovable
    0.08
    Activations Density 0.006%

    No Known Activations