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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 90541
    Prev
    Next
    INDEX
    Explanations

    unning

    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
     valor
    -0.10
    徐
    -0.08
     solvent
    -0.08
    valor
    -0.08
    _prop
    -0.08
    â
    -0.07
     vigorously
    -0.07
     vastly
    -0.07
     largely
    -0.07
     brav
    -0.07
    POSITIVE LOGITS
    	module
    0.09
     module
    0.09
     פעם
    0.09
    .Results
    0.08
    週間
    0.08
     Maio
    0.08
     manager
    0.08
     Elections
    0.08
    .results
    0.08
     Nouveau
    0.08
    Activations Density 0.060%

    No Known Activations