© 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. 19-RESID-POST-AA
    11. 102676
    Prev
    Next
    INDEX
    Explanations

    Foreign language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     большинства
    -0.08
    /account
    -0.08
    nika
    -0.08
    major
    -0.08
    /category
    -0.08
    /help
    -0.08
    /how
    -0.07
    ashire
    -0.07
    —from
    -0.07
    /text
    -0.07
    POSITIVE LOGITS
     plusieurs
    0.08
     leuwih
    0.08
    ّل
    0.08
     shutting
    0.08
     nekoliko
    0.08
    加入
    0.08
    更多
    0.08
     başarı
    0.08
     exclusivement
    0.08
     Quelques
    0.08
    Activations Density 0.002%

    No Known Activations