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. 49826
    Prev
    Next
    INDEX
    Explanations

    ilateral

    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
     Leistung
    -0.07
    紙
    -0.07
     PPE
    -0.07
     bleach
    -0.07
    imei
    -0.07
     דרך
    -0.07
    .axes
    -0.07
     Kodi
    -0.07
    rch
    -0.07
     وقع
    -0.07
    POSITIVE LOGITS
     అంటే
    0.09
     characterized
    0.08
    -rated
    0.08
    ,即
    0.08
     limo
    0.08
     એટલે
    0.08
     viv
    0.08
    —that
    0.08
     conclusion
    0.08
    viv
    0.07
    Activations Density 0.046%

    No Known Activations