© 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. 606
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
    了解
    -0.08
    理解
    -0.08
    clerosis
    -0.08
    不了
    -0.08
     pessoa
    -0.08
    判断
    -0.07
    lafen
    -0.07
     indirectly
    -0.07
     kişinin
    -0.07
     lidi
    -0.07
    POSITIVE LOGITS
     предусматри
    0.09
     Equipped
    0.09
     থাকবে
    0.08
     тщательно
    0.08
     revamped
    0.08
     предусмотр
    0.08
    0.08
     സംവിധാനം
    0.08
     planned
    0.08
     حملة
    0.08
    Activations Density 0.055%
    No Known Activations