© 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. 44843
    Prev
    Next
    INDEX
    Explanations

    safety

    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
     shug
    -0.09
     meng
    -0.08
     Portuguesa
    -0.08
     vět
    -0.07
     уй
    -0.07
     Ž
    -0.07
     Samb
    -0.07
    _disconnect
    -0.07
     luminos
    -0.07
     mai
    -0.07
    POSITIVE LOGITS
    gefühl
    0.09
     instincts
    0.08
    gevoel
    0.08
    xiom
    0.08
    chat
    0.08
    /usr
    0.08
     छु
    0.08
    cla
    0.08
     महसूस
    0.08
    ilda
    0.07
    Activations Density 0.007%

    No Known Activations