© 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. 3
    Prev
    Next
    INDEX
    Explanations

    instruction

    np_max-act · gemini-2.0-flash

    phrases in prompt headers that explicitly signal task directives or instructions to follow.

    oai_token-act-pair · gpt-5Triggered by @liuliujiujiu05
    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
     স্বাস্থ্য
    -0.08
    ỏng
    -0.08
    PID
    -0.08
     Rolling
    -0.08
     Hanging
    -0.08
     MGM
    -0.08
     Appetite
    -0.07
     PID
    -0.07
     Nights
    -0.07
     Männer
    -0.07
    POSITIVE LOGITS
    /em
    0.09
     espada
    0.08
    _fonts
    0.08
     tomando
    0.08
     multimedia
    0.08
    iglio
    0.08
    Font
    0.08
    font
    0.08
     sur
    0.08
     tomar
    0.08
    Activations Density 0.012%

    No Known Activations