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. 65223
    Prev
    Next
    INDEX
    Explanations

    *y

    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
    비스
    -0.08
     Du
    -0.08
     embodies
    -0.08
     Hygiene
    -0.07
     Hers
    -0.07
     Pope
    -0.07
     toaster
    -0.07
     Principle
    -0.07
     teaches
    -0.07
    igator
    -0.07
    POSITIVE LOGITS
    Sus
    0.08
    بادل
    0.08
     disparity
    0.08
    (nil
    0.08
     वाली
    0.08
     Sus
    0.08
    ിന്ന
    0.08
    _tests
    0.08
     प्रस्तुत
    0.07
     apresentados
    0.07
    Activations Density 0.010%

    No Known Activations