© 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. 21642
    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
     específicas
    -0.11
     relacionadas
    -0.10
     related
    -0.09
     inimese
    -0.09
     rápidas
    -0.09
     kişinin
    -0.09
    .related
    -0.09
     ребенку
    -0.09
     адамның
    -0.09
     liées
    -0.08
    POSITIVE LOGITS
    who
    0.15
     الذين
    0.14
     who've
    0.14
     who
    0.14
    দের
    0.14
     rejoice
    0.14
     którzy
    0.14
     যারা
    0.14
    chaft
    0.13
    에게
    0.13
    Activations Density 0.078%

    No Known Activations