© 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. 20437
    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
     "
    -0.13
     only
    -0.11
    或者
    -0.09
     только
    -0.09
     somewhat
    -0.09
     ones
    -0.09
    -0.08
     possibly
    -0.08
     ">↵
    -0.08
     interesting
    -0.08
    POSITIVE LOGITS
    -Based
    0.12
    》中
    0.10
    »-
    0.10
     నేపథ్యంలో
    0.10
    …………………………………………
    0.10
    .อ
    0.10
    〕
    0.10
    0.09
     versus
    0.09
    .ส
    0.09
    Activations Density 0.035%

    No Known Activations