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. 65235
    Prev
    Next
    INDEX
    Explanations

    点

    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
     Cabr
    -0.08
     dziew
    -0.08
     Aufmerksamkeit
    -0.08
     atención
    -0.08
     Maggie
    -0.08
    ('@/
    -0.07
    क्स
    -0.07
     uro
    -0.07
     amoureux
    -0.07
    ാട
    -0.07
    POSITIVE LOGITS
     creed
    0.08
     succinct
    0.08
     배열
    0.07
     explicitly
    0.07
     mantra
    0.07
     lofty
    0.07
     내용
    0.07
    =""
    0.07
     વિડ
    0.07
     ভিত
    0.07
    Activations Density 0.002%

    No Known Activations