© 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. 70173
    Prev
    Next
    INDEX
    Explanations

    a

    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
     divisor
    -0.09
     indulg
    -0.08
     meno
    -0.08
     مشاهده
    -0.07
    େ
    -0.07
     acquaintances
    -0.07
     administrator
    -0.07
     nast
    -0.07
     deja
    -0.07
     acquaintance
    -0.07
    POSITIVE LOGITS
     spacecraft
    0.15
     डिजाइन
    0.10
    研发
    0.10
     aboard
    0.10
     waterproof
    0.09
     утеп
    0.09
     кораб
    0.09
     onboard
    0.09
     ഒരുക്ക
    0.09
     обеспеч
    0.09
    Activations Density 0.017%

    No Known Activations