© 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. 22253
    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
    och
    -0.09
    eken
    -0.08
    jon
    -0.08
    ort
    -0.08
    :is
    -0.08
    orship
    -0.08
    UF
    -0.08
    ma
    -0.08
    izat
    -0.07
    uf
    -0.07
    POSITIVE LOGITS
    ։↵
    0.09
     մեկն
    0.09
     امله
    0.09
     अस्प
    0.09
     Might
    0.08
    ։↵↵
    0.08
    τικών
    0.08
     Sekunden
    0.08
     պատճառով
    0.08
     गौर
    0.08
    Activations Density 0.006%

    No Known Activations