© 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. 30396
    Prev
    Next
    INDEX
    Explanations

    the

    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
     olimp
    -0.08
    开的
    -0.08
    ical
    -0.08
    entscheid
    -0.08
    ()</
    -0.08
    dere
    -0.07
     انقلاب
    -0.07
    DNS
    -0.07
    latex
    -0.07
    ajax
    -0.07
    POSITIVE LOGITS
     Ausstattung
    0.10
     wyposaż
    0.10
     adorned
    0.10
    豪
    0.10
    最低
    0.10
     luxurious
    0.09
     luxuri
    0.09
     Airbus
    0.09
     accessories
    0.09
     finition
    0.09
    Activations Density 0.022%

    No Known Activations