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. 52867
    Prev
    Next
    INDEX
    Explanations

    Lengthy text passages

    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
     Dabei
    -0.08
     reached
    -0.08
    style
    -0.08
     remarkably
    -0.07
    Seed
    -0.07
     stunning
    -0.07
     seed
    -0.07
    seed
    -0.07
    স্থান
    -0.07
    .nd
    -0.07
    POSITIVE LOGITS
    Nevertheless
    0.10
     terlalu
    0.09
     слишком
    0.09
     unintended
    0.09
     undesirable
    0.08
     affairs
    0.08
    Nonetheless
    0.08
     Fortunately
    0.08
     Nevertheless
    0.08
     Remedy
    0.08
    Activations Density 0.165%

    No Known Activations