© 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. 47883
    Prev
    Next
    INDEX
    Explanations

    XML tags

    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
    tir
    -0.09
    aknya
    -0.08
     μπορεί
    -0.08
    ...)
    -0.08
    ...).
    -0.08
     oscill
    -0.08
     bipolar
    -0.07
    osc
    -0.07
     based
    -0.07
     firme
    -0.07
    POSITIVE LOGITS
     Biotechnology
    0.08
    み
    0.08
     চেষ্টা
    0.08
    附件
    0.07
    最新版
    0.07
     Acts
    0.07
    ーパ
    0.07
     Ergän
    0.07
     попыт
    0.07
     груз
    0.07
    Activations Density 0.002%

    No Known Activations