© 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. 94809
    Prev
    Next
    INDEX
    Explanations

    exercise

    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
    оян
    -0.08
     Computer
    -0.08
     hacía
    -0.07
    'nın
    -0.07
     Quest
    -0.07
    Quest
    -0.07
    Computer
    -0.07
     Spiral
    -0.07
     наруш
    -0.07
    СК
    -0.07
    POSITIVE LOGITS
     caution
    0.09
     pli
    0.08
    mnt
    0.08
    弊
    0.08
     undertaken
    0.08
     geste
    0.08
    兵
    0.07
    imonial
    0.07
     ses
    0.07
     ken
    0.07
    Activations Density 0.012%

    No Known Activations