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. 45617
    Prev
    Next
    INDEX
    Explanations

    2

    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
     certified
    -0.09
     adobe
    -0.08
     превос
    -0.08
     Certified
    -0.08
    Certified
    -0.08
     underserved
    -0.08
     circunstancias
    -0.08
    	ob
    -0.08
    PTS
    -0.08
     कोरो
    -0.08
    POSITIVE LOGITS
     కంపెన
    0.08
    滚
    0.08
     barn
    0.08
     MDC
    0.08
     trims
    0.08
     depósito
    0.08
     peanuts
    0.07
    (None
    0.07
     నివ
    0.07
    ‌ని
    0.07
    Activations Density 0.001%

    No Known Activations