© 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. 45226
    Prev
    Next
    INDEX
    Explanations

    needs

    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
    �
    -0.08
    ";↵/
    -0.08
     mila
    -0.07
    について
    -0.07
    nat
    -0.07
     ergo
    -0.07
    共同
    -0.07
     yin
    -0.07
     lem
    -0.07
     lwa
    -0.07
    POSITIVE LOGITS
     Rein
    0.08
     فائد
    0.08
    .new
    0.08
     التجاري
    0.08
    IDGET
    0.08
     نوي
    0.07
     Нов
    0.07
    راً
    0.07
     ẹgbẹ
    0.07
    crement
    0.07
    Activations Density 0.000%

    No Known Activations