© 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. 19357
    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
    storms
    -0.09
     derni
    -0.08
    Glass
    -0.08
    _EMPTY
    -0.08
     jurisdictions
    -0.08
    MASTER
    -0.08
    .latest
    -0.08
     الجديدة
    -0.08
    .identity
    -0.08
    _latest
    -0.08
    POSITIVE LOGITS
     longitud
    0.09
     comprimento
    0.09
     اولیه
    0.08
     normaal
    0.08
    իս
    0.08
     کامل
    0.08
     normalen
    0.08
     základ
    0.08
    本科
    0.08
     khoom
    0.08
    Activations Density 0.010%

    No Known Activations