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. 65220
    Prev
    Next
    INDEX
    Explanations

    bed

    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
     soar
    -0.08
     allegations
    -0.08
     Airports
    -0.08
     مالية
    -0.08
     Attendance
    -0.08
     Chung
    -0.07
     intrins
    -0.07
     AOL
    -0.07
    考试
    -0.07
     competências
    -0.07
    POSITIVE LOGITS
     участка
    0.10
     minced
    0.09
     beginners
    0.09
     pequeño
    0.08
     earnest
    0.08
     recept
    0.08
     portion
    0.08
     участок
    0.08
    0.08
     subsection
    0.08
    Activations Density 0.016%

    No Known Activations