© 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. 11-RESID-POST-AA
    11. 99131
    Prev
    Next
    INDEX
    Explanations

    juice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Hoffman
    -0.09
     excellence
    -0.09
     ஒன்ற
    -0.09
     Mö
    -0.08
     mia
    -0.08
    {}{
    -0.08
     bespre
    -0.08
     ஒன்று
    -0.08
     Bes
    -0.08
     �
    -0.07
    POSITIVE LOGITS
     marinade
    0.10
     conco
    0.10
    opacity
    0.07
    ást
    0.07
    .normalize
    0.07
     বের
    0.07
     сущ
    0.07
    -Christ
    0.07
     régulièrement
    0.07
     obsah
    0.07
    Activations Density 0.005%

    No Known Activations