© 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. 94976
    Prev
    Next
    INDEX
    Explanations

    Semiotics

    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
    日本
    -0.08
     Deferred
    -0.07
    炸
    -0.07
    kal
    -0.07
    中国
    -0.07
    dog
    -0.07
    USD
    -0.07
     Coinbase
    -0.07
     Mim
    -0.07
     sienten
    -0.07
    POSITIVE LOGITS
     ফর
    0.09
     journey
    0.09
     сказ
    0.09
     неис
    0.09
     науки
    0.08
     Arden
    0.08
     principles
    0.08
     bore
    0.08
     специалист
    0.08
     Burg
    0.08
    Activations Density 0.001%

    No Known Activations