© 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. 19616
    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
    ално
    -0.09
    formin
    -0.08
     Hess
    -0.08
    ална
    -0.08
     surgeons
    -0.08
    %\
    -0.08
    존
    -0.08
    Skeleton
    -0.07
    ални
    -0.07
    obian
    -0.07
    POSITIVE LOGITS
     constellation
    0.11
     volk
    0.10
    voq
    0.09
    qam
    0.09
     Communications
    0.08
     bloco
    0.08
     jammer
    0.08
    短
    0.08
     waterfall
    0.08
     Communication
    0.08
    Activations Density 0.002%

    No Known Activations