© 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. 25871
    Prev
    Next
    INDEX
    Explanations

    Chinese language

    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
     apoi
    -0.08
     Gil
    -0.08
     ಪ್ರಕಟ
    -0.07
     issuer
    -0.07
     Specifies
    -0.07
     wijzig
    -0.07
     guitarist
    -0.07
    主人
    -0.07
     parce
    -0.07
     tomato
    -0.07
    POSITIVE LOGITS
     bü
    0.09
    adat
    0.09
     بس
    0.09
     Zd
    0.08
    容易
    0.08
    Bought
    0.08
    ài
    0.08
     megh
    0.08
    Zd
    0.07
    略
    0.07
    Activations Density 0.001%

    No Known Activations