© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 96859
    Prev
    Next
    INDEX
    Explanations

    sterilization and disinfection

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     үл
    -0.08
     防
    -0.08
    ಾವಣೆ
    -0.08
     Anlass
    -0.08
    ಾವಣ
    -0.08
    abilirsiniz
    -0.08
     unkompl
    -0.08
     halinde
    -0.08
     puoi
    -0.08
    -To
    -0.08
    POSITIVE LOGITS
    221
    0.08
    121
    0.08
     rů
    0.08
     Nij
    0.07
    ijf
    0.07
    222
    0.07
     surgery
    0.07
     sitting
    0.07
     seconds
    0.07
     nny
    0.07
    Activations Density 0.001%

    No Known Activations