© 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. 19-RESID-POST-AA
    11. 19107
    Prev
    Next
    INDEX
    Explanations

    choose

    np_max-act-logits · gemini-2.0-flash
    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
     bliver
    -0.10
     blir
    -0.09
     привык
    -0.09
    .Unknown
    -0.09
    irap
    -0.08
     ถูก
    -0.08
     buruz
    -0.08
     miatt
    -0.08
    ınd
    -0.08
    Mientras
    -0.08
    POSITIVE LOGITS
     choose
    0.19
     Можно
    0.18
     Choose
    0.17
     можно
    0.17
    可以
    0.17
    choose
    0.16
    Choose
    0.16
     podemos
    0.16
     näiteks
    0.16
    Можно
    0.16
    Activations Density 0.090%

    No Known Activations