© 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. 22468
    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
     and
    -0.10
     และ
    -0.08
    isert
    -0.08
     وأس
    -0.08
    HING
    -0.08
     привести
    -0.08
     ఎ
    -0.08
     कितना
    -0.07
    ambled
    -0.07
     Seeing
    -0.07
    POSITIVE LOGITS
     application
    0.10
     }↵
    0.09
     caractère
    0.08
     recherche
    0.08
     connue
    0.08
    Deux
    0.08
     rapide
    0.08
     définit
    0.08
    _application
    0.08
     boutons
    0.08
    Activations Density 0.005%

    No Known Activations