© 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. 78972
    Prev
    Next
    INDEX
    Explanations

    ада

    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
     toss
    -0.08
    呵
    -0.08
     smith
    -0.08
     hurried
    -0.08
     Horn
    -0.08
     �
    -0.08
    iales
    -0.08
    tty
    -0.08
     Sis
    -0.07
    ให้
    -0.07
    POSITIVE LOGITS
    属于
    0.10
    属
    0.09
    한다
    0.08
    enzeka
    0.08
     milions
    0.08
     belonged
    0.08
    ირდება
    0.07
    하도록
    0.07
    ència
    0.07
     करोड़
    0.07
    Activations Density 0.066%

    No Known Activations