© 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. 20237
    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
    -haired
    -0.11
    /cloud
    -0.11
     волос
    -0.10
     волосы
    -0.10
    -fluid
    -0.10
    -cloud
    -0.10
    -elect
    -0.09
    (火
    -0.09
    -tree
    -0.09
     воду
    -0.09
    POSITIVE LOGITS
     små
    0.09
     transferred
    0.08
     reclaimed
    0.08
     tiny
    0.08
     lowered
    0.08
     honderden
    0.08
     inverted
    0.08
     diced
    0.08
     piccoli
    0.07
     regenerated
    0.07
    Activations Density 0.004%

    No Known Activations