© 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. 99354
    Prev
    Next
    INDEX
    Explanations

    to

    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
     būti
    -0.09
     impur
    -0.08
    окуп
    -0.08
    ircuit
    -0.08
    उत्तर
    -0.07
     ಉತ್ತರ
    -0.07
     ընտ
    -0.07
     --------------------------------------------------------------------------------
    -0.07
     atento
    -0.07
    -0.07
    POSITIVE LOGITS
     рассчит
    0.10
     предусмотр
    0.09
     checks
    0.09
     relies
    0.09
    checks
    0.09
     originally
    0.08
     designed
    0.08
    expects
    0.08
     empfind
    0.08
     reliant
    0.08
    Activations Density 0.025%

    No Known Activations