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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12848
    Prev
    Next
    INDEX
    Explanations

    Taj Mahal

    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
     manchmal
    -0.09
     Accredited
    -0.08
     boul
    -0.08
    altet
    -0.08
     sometimes
    -0.08
     ibland
    -0.08
     further
    -0.07
     entdecken
    -0.07
     hoses
    -0.07
     Sometimes
    -0.07
    POSITIVE LOGITS
     স্ত্রী
    0.09
     ഭാര്യ
    0.09
     पत्नी
    0.09
     પત્ન
    0.09
     cool
    0.09
     esposa
    0.09
     coolest
    0.08
     vanity
    0.08
     wife
    0.08
     farewell
    0.08
    Activations Density 0.005%

    No Known Activations