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. 88211
    Prev
    Next
    INDEX
    Explanations

    Locke & Latham theory

    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
     hillside
    -0.09
     gson
    -0.09
     kafka
    -0.08
     downhill
    -0.08
     efectiva
    -0.08
     you'll
    -0.08
     shap
    -0.08
     дед
    -0.07
     docker
    -0.07
     necesaria
    -0.07
    POSITIVE LOGITS
    -report
    0.09
     Export
    0.08
    _REPORT
    0.08
    633
    0.08
    Export
    0.08
    -j
    0.08
    REPORT
    0.08
     Reporting
    0.08
     Interviews
    0.07
    ieks
    0.07
    Activations Density 0.002%

    No Known Activations