© 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. 19-RESID-POST-AA
    11. 102633
    Prev
    Next
    INDEX
    Explanations

    background

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     怎么
    -0.10
    .cap
    -0.08
     如何
    -0.08
     быць
    -0.08
     AVAILABLE
    -0.08
     CLOSED
    -0.08
     määrä
    -0.08
     مقدار
    -0.08
     nostri
    -0.08
     કરવાની
    -0.08
    POSITIVE LOGITS
     background
    0.15
     الخلف
    0.14
     surroundings
    0.14
     backgrounds
    0.14
     achtergrond
    0.14
     foreground
    0.13
    背景
    0.13
    _background
    0.13
     ಹಿನ್ನೆ
    0.13
     خلف
    0.12
    Activations Density 0.003%

    No Known Activations