© 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 EvalsExportsAPI 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. 20811
    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
     kalau
    -0.08
     volonté
    -0.08
     jeśli
    -0.08
     if
    -0.08
    705
    -0.08
     如果
    -0.08
    在
    -0.07
     flere
    -0.07
    elsch
    -0.07
     Eğer
    -0.07
    POSITIVE LOGITS
     behave
    0.10
    bereiche
    0.10
    ,use
    0.09
     অংশ
    0.09
     nggunakake
    0.09
     арнал
    0.09
    räume
    0.09
     doeleinden
    0.08
    ,on
    0.08
     uporabo
    0.08
    Activations Density 0.027%

    No Known Activations