© 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. 29580
    Prev
    Next
    INDEX
    Explanations

    Journal issue or of

    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
     género
    -0.08
     पूरा
    -0.08
     अच्छा
    -0.07
     scandals
    -0.07
     ponct
    -0.07
    ethylene
    -0.07
     maravilloso
    -0.07
     Wey
    -0.07
     കല
    -0.07
     Rezension
    -0.07
    POSITIVE LOGITS
     होगी
    0.10
     navy
    0.09
     ہوگی
    0.09
     it'll
    0.09
     trunks
    0.08
     he'll
    0.08
     થશે
    0.08
     plans
    0.08
    予定
    0.08
    ľ
    0.08
    Activations Density 0.022%

    No Known Activations