© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 26208
    Prev
    Next
    INDEX
    Explanations

    math

    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
    †
    -0.09
    plus
    -0.08
    就
    -0.08
    飞
    -0.07
    ся
    -0.07
    ，还有
    -0.07
     unmet
    -0.07
     mohou
    -0.07
    Ec
    -0.07
    เพื่อ
    -0.07
    POSITIVE LOGITS
     Estat
    0.08
     sidste
    0.08
     Ita
    0.08
     Kino
    0.08
     Stadion
    0.08
     Tiv
    0.07
    ошт
    0.07
     ???↵↵
    0.07
     culmination
    0.07
     Stanton
    0.07
    Activations Density 0.041%

    No Known Activations