© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 21015
    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
     Peu
    -0.08
    VRTX
    -0.08
    ittu
    -0.07
     ఆస
    -0.07
     చాలా
    -0.07
     öfter
    -0.07
     కొ
    -0.07
     semakin
    -0.07
     ενδια
    -0.07
    Tow
    -0.07
    POSITIVE LOGITS
     allein
    0.20
     alleine
    0.19
     alone
    0.19
     alene
    0.18
    万能
    0.17
     अके
    0.17
     solely
    0.16
     sole
    0.16
     Alone
    0.16
     sozinho
    0.15
    Activations Density 0.020%

    No Known Activations