Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 404
    Prev
    Next
    INDEX
    Explanations

    control/export regulations

    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
     toast
    -0.08
    ferred
    -0.08
    Оч
    -0.07
    પણ
    -0.07
     бренд
    -0.07
     gemiddeld
    -0.07
    жет
    -0.07
    tel
    -0.07
     smoothies
    -0.07
     aided
    -0.07
    POSITIVE LOGITS
     sanctions
    0.09
     பூ
    0.08
     siyaas
    0.08
     governmental
    0.08
     அரச
    0.08
     правила
    0.08
    ศ
    0.08
     Jew
    0.08
     спе
    0.08
    esar
    0.08
    Activations Density 0.005%

    No Known Activations