© 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. 939
    Prev
    Next
    INDEX
    Explanations

    ers

    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
    Advisor
    -0.08
     dadas
    -0.08
    chairs
    -0.08
    ighthouse
    -0.08
     пул
    -0.07
     cellar
    -0.07
     یو
    -0.07
     muid
    -0.07
    uesday
    -0.07
    <<<<
    -0.07
    POSITIVE LOGITS
    สามารถ
    0.09
     sollten
    0.09
    需
    0.08
     podrán
    0.08
    须
    0.08
     Beware
    0.08
     زیادی
    0.08
     treba
    0.08
    vaient
    0.08
     eset
    0.08
    Activations Density 0.240%

    No Known Activations