© 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. 20003
    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
    -ийн
    -0.09
    न्होंने
    -0.09
     מדובר
    -0.09
    -жылдын
    -0.09
     aangegeven
    -0.09
    treated
    -0.09
     ಇದು
    -0.09
    是真的假的
    -0.09
    adığı
    -0.08
     rencontré
    -0.08
    POSITIVE LOGITS
     ukuze
    0.14
     چاہتے
    0.14
    Чтобы
    0.13
     möglichst
    0.13
     desej
    0.13
     चाहते
    0.12
     desired
    0.12
     चाहता
    0.12
     чтобы
    0.12
     jotta
    0.12
    Activations Density 0.426%

    No Known Activations