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. 61084
    Prev
    Next
    INDEX
    Explanations

    end marker

    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
    Tenemos
    -0.09
     secretary
    -0.08
     عقل
    -0.08
    。那么
    -0.08
     radicals
    -0.08
     موقف
    -0.08
     forbind
    -0.08
    桶
    -0.08
     όμως
    -0.08
    	utils
    -0.08
    POSITIVE LOGITS
    Hope
    0.08
     concludes
    0.08
     Espero
    0.08
     hereby
    0.08
     neatly
    0.08
     Sorry
    0.08
     adaptation
    0.07
     sorry
    0.07
    usay
    0.07
     narrated
    0.07
    Activations Density 0.013%

    No Known Activations