© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29575
    Prev
    Next
    INDEX
    Explanations

    textbook content

    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
     étaient
    -0.08
    Charles
    -0.08
     éch
    -0.08
     tún
    -0.08
    ਂ
    -0.08
     hypoc
    -0.08
    Morph
    -0.08
     улыб
    -0.07
     sourire
    -0.07
     morphology
    -0.07
    POSITIVE LOGITS
     प्रश्न
    0.11
    sidebar
    0.10
     Übungen
    0.09
     упражнения
    0.09
     Exercises
    0.09
    .questions
    0.09
     ಪ್ರಶ್ನ
    0.09
     ejercicios
    0.09
    ollars
    0.09
     exercícios
    0.09
    Activations Density 0.034%

    No Known Activations