© 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. 19545
    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
     方法
    -0.08
    Yep
    -0.08
    737
    -0.08
    736
    -0.08
    ٌ
    -0.08
    126
    -0.08
    624
    -0.08
     Via
    -0.08
     pamamagitan
    -0.08
    738
    -0.08
    POSITIVE LOGITS
    ирования
    0.12
    изации
    0.11
    ización
    0.10
    μού
    0.10
    ования
    0.10
    рования
    0.10
    социа
    0.10
    achaidh
    0.09
    дения
    0.09
    owego
    0.09
    Activations Density 0.142%

    No Known Activations