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. 11877
    Prev
    Next
    INDEX
    Explanations

    ServiceNow documentation/code

    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
     Esperanto
    -0.10
     socks
    -0.10
     extrater
    -0.09
     clap
    -0.09
     earbuds
    -0.09
     vocals
    -0.09
     ruining
    -0.09
     percept
    -0.09
     glfw
    -0.09
     гармони
    -0.09
    POSITIVE LOGITS
    审批
    0.14
     Magento
    0.13
    审核
    0.12
     Drupal
    0.12
    Audit
    0.12
     Salesforce
    0.12
     Audit
    0.12
    .liferay
    0.12
    Magento
    0.11
    Portlet
    0.11
    Activations Density 0.036%

    No Known Activations