Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 113067
    Prev
    Next
    INDEX
    Explanations

    RMB, international, Chinese

    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
     faulty
    -0.08
     assembly
    -0.08
     assembled
    -0.07
     easy
    -0.07
     intersection
    -0.07
     colet
    -0.07
     disting
    -0.07
    व
    -0.07
     conselho
    -0.07
     विज
    -0.07
    POSITIVE LOGITS
     Offshore
    0.09
     lounges
    0.09
     лас
    0.08
    Sandbox
    0.08
    Restrictions
    0.08
    -Lo
    0.08
    Scopes
    0.08
    lho
    0.08
     Transpar
    0.08
    caps
    0.08
    Activations Density 0.005%

    No Known Activations