© 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. 78444
    Prev
    Next
    INDEX
    Explanations

    ‑

    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
     pemain
    -0.08
    违法
    -0.08
     ayrıca
    -0.08
     skier
    -0.08
    -find
    -0.08
     breach
    -0.07
    DOS
    -0.07
     quindi
    -0.07
    例如
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    ™s
    0.09
     inspired
    0.08
     creë
    0.08
     distilled
    0.08
    &eacute
    0.07
     creëren
    0.07
    gable
    0.07
     considering
    0.07
    ี้ย
    0.07
    ✨
    0.07
    Activations Density 0.018%

    No Known Activations