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. 90655
    Prev
    Next
    INDEX
    Explanations

    multiple choice answers

    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
     impostos
    -0.08
    Taxes
    -0.08
     heur
    -0.08
    boats
    -0.08
    SCRIPT
    -0.08
     impuestos
    -0.08
     Taxes
    -0.07
     departed
    -0.07
    objs
    -0.07
    xffff
    -0.07
    POSITIVE LOGITS
    编号
    0.09
    _register
    0.09
    /A
    0.09
     Register
    0.08
     نمبر
    0.08
     registre
    0.08
     register
    0.08
     등록
    0.08
     numbered
    0.08
    	register
    0.08
    Activations Density 0.047%

    No Known Activations