© 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. 102614
    Prev
    Next
    INDEX
    Explanations

    Urban

    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
    manufacturer
    -0.10
    ന്യൂ
    -0.09
    -integr
    -0.08
    manageable
    -0.08
    quantity
    -0.08
    elijkse
    -0.08
     Юж
    -0.08
    managed
    -0.08
     Helsing
    -0.08
    ‌توان
    -0.08
    POSITIVE LOGITS
     dhaq
    0.08
     DEALINGS
    0.08
     arbete
    0.08
    อด
    0.08
    향
    0.08
    อกจาก
    0.08
    ๋
    0.07
     underlying
    0.07
     andando
    0.07
     famb
    0.07
    Activations Density 0.003%

    No Known Activations