© 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. 21040
    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
    ಿತ್ಯ
    -0.10
    _available
    -0.09
     tilgjeng
    -0.09
    cé
    -0.08
    _tot
    -0.08
    fügbarkeit
    -0.08
     inherit
    -0.08
     katerih
    -0.08
     mempun
    -0.08
    -normal
    -0.08
    POSITIVE LOGITS
     =
    0.08
     is
    0.07
     voidaan
    0.07
     என்பது
    0.07
     hoort
    0.07
     palav
    0.07
    ARG
    0.07
     سوال
    0.07
     okwu
    0.07
     bevindt
    0.07
    Activations Density 0.000%

    No Known Activations