© 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. 108654
    Prev
    Next
    INDEX
    Explanations

    こと

    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
    pä
    -0.09
     intrinsic
    -0.08
    пы
    -0.08
    dä
    -0.07
    dab
    -0.07
     Rah
    -0.07
    fäh
    -0.07
    pump
    -0.07
     TAS
    -0.07
    p
    -0.07
    POSITIVE LOGITS
    示
    0.10
     supr
    0.08
    、お
    0.08
     গুরুত্ব
    0.08
     आग
    0.08
    御
    0.08
     suprem
    0.08
     bitcoin
    0.08
    ованием
    0.08
     소개
    0.08
    Activations Density 0.002%

    No Known Activations