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

    Neuronpedia

    APICircuit 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. 30579
    Prev
    Next
    INDEX
    Explanations

    APIs and services

    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
     lith
    -0.09
    curve
    -0.09
     situaciones
    -0.08
     situations
    -0.08
     troubleshoot
    -0.08
    printed
    -0.08
     Printed
    -0.08
     procrast
    -0.08
     troubleshooting
    -0.08
    Printed
    -0.08
    POSITIVE LOGITS
     API
    0.17
    _api
    0.14
    API
    0.13
    _API
    0.13
    -api
    0.13
     APIs
    0.12
    /api
    0.11
    	api
    0.11
    .api
    0.11
    接口
    0.10
    Activations Density 0.015%

    No Known Activations