© 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. 19678
    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
    s
    -0.16
    a
    -0.15
    some
    -0.14
    x
    -0.13
    this
    -0.13
    ️
    -0.12
    sx
    -0.12
    M
    -0.12
    simp
    -0.12
    both
    -0.12
    POSITIVE LOGITS
    -thirds
    0.19
    fold
    0.17
    teenth
    0.16
    жды
    0.16
     hundred
    0.15
     번째
    0.15
    ième
    0.14
    -four
    0.13
    teen
    0.13
     વખત
    0.13
    Activations Density 0.223%

    No Known Activations