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. 45199
    Prev
    Next
    INDEX
    Explanations

    ath

    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
     המת
    -0.08
    .“
    -0.07
    �
    -0.07
    排行
    -0.07
    크
    -0.07
    人体
    -0.07
    )";↵
    -0.07
    umé
    -0.07
    .size
    -0.07
    ental
    -0.07
    POSITIVE LOGITS
     ವಿ�
    0.08
     jaunes
    0.07
     propiet
    0.07
     pess
    0.07
    ्त
    0.07
    தில்
    0.07
     Thess
    0.07
     trustee
    0.07
     betaald
    0.07
    stas
    0.07
    Activations Density 0.003%

    No Known Activations