© 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. 21330
    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
    的
    -0.08
    iali
    -0.08
     these
    -0.08
    ione
    -0.08
     underlying
    -0.08
    ing
    -0.07
    ,
    -0.07
     correspondiente
    -0.07
     nieuwe
    -0.07
     direttamente
    -0.07
    POSITIVE LOGITS
    Third
    0.14
     dritten
    0.14
     troisième
    0.14
     third
    0.14
     треть
    0.14
     മൂന്ന
    0.14
     tredje
    0.14
     dritte
    0.13
     Third
    0.13
     derde
    0.13
    Activations Density 0.036%

    No Known Activations