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. 49075
    Prev
    Next
    INDEX
    Explanations

    Language structure and properties

    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
     pintura
    -0.08
    Via
    -0.07
     damp
    -0.07
    elis
    -0.07
    IEEE
    -0.07
    seri
    -0.07
     IEEE
    -0.06
     erosion
    -0.06
     infring
    -0.06
     javax
    -0.06
    POSITIVE LOGITS
     अके
    0.08
     ছোট
    0.08
    -bodied
    0.08
     uwezo
    0.08
     Placeholder
    0.08
     kiwango
    0.08
     التداول
    0.08
     ngunit
    0.08
    atoa
    0.08
    esture
    0.08
    Activations Density 0.017%

    No Known Activations