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. 27514
    Prev
    Next
    INDEX
    Explanations

    Clarifications/Edits

    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
    。那么
    -0.09
     
    -0.09
    Locator
    -0.08
     yaran
    -0.08
    Lots
    -0.08
     lots
    -0.08
    ورو
    -0.08
    有什么
    -0.08
    。我
    -0.08
    	top
    -0.08
    POSITIVE LOGITS
     traditionally
    0.08
    .adjust
    0.08
    맥
    0.08
     helaas
    0.08
     inaccur
    0.08
    asks
    0.08
     here
    0.08
     misleading
    0.07
    ayment
    0.07
     потребуется
    0.07
    Activations Density 0.153%

    No Known Activations