© 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. 19530
    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
     '
    -0.08
     "
    -0.08
    -0.08
     es
    -0.08
     *
    -0.08
     által
    -0.07
    -0.07
     cada
    -0.07
     wassen
    -0.07
    !,
    -0.07
    POSITIVE LOGITS
     thoroughly
    0.13
     хорошо
    0.12
     daradara
    0.12
     together
    0.11
     સારી
    0.11
     добре
    0.11
     until
    0.11
     hanggang
    0.11
     miteinander
    0.11
     vizuri
    0.11
    Activations Density 0.006%
    No Known Activations