© 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. 24790
    Prev
    Next
    INDEX
    Explanations

    gas

    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
     mois
    -0.08
    woo
    -0.07
     within
    -0.07
     circular
    -0.07
    Winning
    -0.07
     prison
    -0.07
     peyi
    -0.07
     winning
    -0.07
    Within
    -0.07
    天下
    -0.07
    POSITIVE LOGITS
     staffed
    0.10
     оборуд
    0.09
     attendants
    0.09
    设施
    0.09
     commerciale
    0.09
     시설
    0.09
    /operators
    0.09
     দোক
    0.09
    stations
    0.09
     వద్ద
    0.09
    Activations Density 0.007%

    No Known Activations