© 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. 94796
    Prev
    Next
    INDEX
    Explanations

    educational 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
     olaraq
    -0.09
    Transient
    -0.08
    _requested
    -0.08
    _duplicate
    -0.08
    Choice
    -0.07
    empt
    -0.07
    _choice
    -0.07
    ("""↵
    -0.07
    _clone
    -0.07
    lang
    -0.07
    POSITIVE LOGITS
     basics
    0.12
     Basics
    0.12
     básico
    0.11
     Bás
    0.11
    Basics
    0.11
     beginners
    0.11
     básicos
    0.11
     básicas
    0.10
     Beginner
    0.10
     basic
    0.09
    Activations Density 0.020%

    No Known Activations