© 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. 68189
    Prev
    Next
    INDEX
    Explanations

    $

    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
    chl
    -0.07
    GS
    -0.07
     involves
    -0.07
     champ
    -0.07
     मंत्र
    -0.07
     allá
    -0.07
     ایف
    -0.07
    .Sys
    -0.07
     Amo
    -0.07
     biểu
    -0.07
    POSITIVE LOGITS
     sores
    0.08
     मिलता
    0.07
     yok
    0.07
     �
    0.07
    optimal
    0.07
    しま
    0.07
     দিয়
    0.07
     ส่วน
    0.07
     మొత్త
    0.07
    unkte
    0.07
    Activations Density 0.086%

    No Known Activations