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. 106169
    Prev
    Next
    INDEX
    Explanations

    ."

    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
    Collector
    -0.08
     Collector
    -0.08
     Lynch
    -0.08
    ੱਜ
    -0.08
    ною
    -0.08
    jan
    -0.07
     nebo
    -0.07
     ataupun
    -0.07
     jan
    -0.07
     lyn
    -0.07
    POSITIVE LOGITS
    Ud
    0.08
     deliver
    0.08
    atar
    0.07
    instructions
    0.07
     Duit
    0.07
     prescriptions
    0.07
     urging
    0.07
     Thesis
    0.07
     prohib
    0.07
     द
    0.07
    Activations Density 0.035%

    No Known Activations