© 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. 30917
    Prev
    Next
    INDEX
    Explanations

    HPV vaccine

    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
    יה
    -0.08
     ভাগ
    -0.08
    udian
    -0.08
     legumes
    -0.07
     kaa
    -0.07
    ，有
    -0.07
    pression
    -0.07
    (end
    -0.07
     ponct
    -0.07
    _END
    -0.07
    POSITIVE LOGITS
     attacker
    0.09
    Courtesy
    0.08
     initiative
    0.08
     प्रशिक्ष
    0.08
     aliaj
    0.08
     rumor
    0.08
     rash
    0.08
     Undert
    0.08
     Trash
    0.08
    upr
    0.08
    Activations Density 0.073%

    No Known Activations