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. 58380
    Prev
    Next
    INDEX
    Explanations

    give

    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
     banken
    -0.08
     Як
    -0.08
     manufacturer's
    -0.08
    银行
    -0.08
    ১৭
    -0.08
     PTR
    -0.08
     ocz
    -0.08
    蒙古
    -0.08
    .Bank
    -0.08
     fabricant
    -0.08
    POSITIVE LOGITS
    hub
    0.08
     recurring
    0.08
     plantea
    0.08
     vuelve
    0.08
    ideos
    0.07
    ствен
    0.07
     lar
    0.07
    ee
    0.07
     nhau
    0.07
    eway
    0.07
    Activations Density 0.002%

    No Known Activations