© 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. 21467
    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
    按照
    -0.09
     നൽകി
    -0.09
     nombreuses
    -0.08
     soit
    -0.08
     nyore
    -0.08
     dictate
    -0.08
     даже
    -0.08
    ':'
    -0.08
     esencia
    -0.08
    .into
    -0.08
    POSITIVE LOGITS
     وعن
    0.19
     поводу
    0.19
     ועל
    0.18
     وكيف
    0.18
     aspects
    0.14
     بارے
    0.14
    について
    0.13
     বিষয়ে
    0.13
    如何
    0.13
    情况
    0.13
    Activations Density 0.507%

    No Known Activations