© 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. 78433
    Prev
    Next
    INDEX
    Explanations

    Japanese language

    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
    .pk
    -0.08
    _pd
    -0.08
    ینہ
    -0.07
     oppervl
    -0.07
     Norm
    -0.07
    -conditioned
    -0.07
    edra
    -0.07
    xia
    -0.07
     aesthetically
    -0.07
     أحدث
    -0.07
    POSITIVE LOGITS
     spelling
    0.09
     用
    0.08
    ทั้งหมด
    0.08
     restantes
    0.08
     trabajando
    0.08
    -record
    0.08
    作文
    0.08
     distracting
    0.08
     handwritten
    0.08
    dig
    0.07
    Activations Density 0.003%

    No Known Activations