© 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. 20701
    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
    ynchronously
    -0.09
    oneksi
    -0.08
    -0.07
    anych
    -0.07
    四
    -0.07
     även
    -0.07
    ុំ
    -0.07
     əlaq
    -0.07
     haɗ
    -0.07
    'є
    -0.07
    POSITIVE LOGITS
     favor
    0.34
    favor
    0.34
     favors
    0.33
    Favor
    0.30
     faveur
    0.29
     favour
    0.29
     favorecer
    0.29
     Favor
    0.29
     favoriser
    0.25
     favore
    0.25
    Activations Density 0.104%
    No Known Activations