© 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. 54660
    Prev
    Next
    INDEX
    Explanations

    dist

    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
     rogue
    -0.08
     Jefferson
    -0.07
     свое
    -0.07
     centrally
    -0.07
     信
    -0.07
     probes
    -0.07
    jego
    -0.07
    _DEN
    -0.07
    Transit
    -0.07
     transit
    -0.07
    POSITIVE LOGITS
    resultado
    0.09
     wynik
    0.08
    成果
    0.08
     adopt
    0.08
    (results
    0.08
     निकाल
    0.08
     نتيجة
    0.08
    াফল
    0.08
     Ergebnisse
    0.08
    étails
    0.08
    Activations Density 0.003%

    No Known Activations