© 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. 19816
    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
    lade
    -0.08
     selben
    -0.08
    ceeded
    -0.08
    -imi
    -0.08
    ovati
    -0.08
     |>
    -0.08
     Несмотря
    -0.07
     trotz
    -0.07
     Despite
    -0.07
     ändå
    -0.07
    POSITIVE LOGITS
     but
    0.20
     மட்ட
    0.19
     മാത്ര
    0.18
    ，但
    0.18
     tetapi
    0.18
     ಮಾತ್ರ
    0.18
     ولكن
    0.18
     लेकिन
    0.18
     laakiin
    0.18
     لكن
    0.17
    Activations Density 0.159%

    No Known Activations