© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 19383
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     তিন
    -0.09
     одном
    -0.09
     మూడు
    -0.09
     cinco
    -0.08
     পাঁচ
    -0.08
    jama
    -0.08
    ('/');↵
    -0.08
     ત્રણ
    -0.08
     εξέ
    -0.08
    -three
    -0.08
    POSITIVE LOGITS
     S
    0.11
     W
    0.11
     B
    0.10
     T
    0.10
     G
    0.10
     D
    0.09
    W
    0.09
    B
    0.09
     C
    0.09
     R
    0.09
    Activations Density 0.014%

    No Known Activations