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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 110649
    Prev
    Next
    INDEX
    Explanations

    mosque

    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
     nihil
    -0.08
    karma
    -0.08
     phoenix
    -0.07
     biệt
    -0.07
    kien
    -0.07
     kalite
    -0.07
     irin
    -0.07
    ヤ
    -0.07
     Napa
    -0.07
     ITEM
    -0.07
    POSITIVE LOGITS
     الكهربائية
    0.09
     Waiting
    0.09
     Mosque
    0.09
     مسجد
    0.09
     halls
    0.09
    Waiting
    0.09
     استقبال
    0.09
     mosque
    0.09
     waiting
    0.09
     المسجد
    0.08
    Activations Density 0.006%

    No Known Activations