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. 9271
    Prev
    Next
    INDEX
    Explanations

    investment return

    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
     분위
    -0.07
     تە
    -0.07
     pregn
    -0.07
     Atmosphäre
    -0.07
     Tone
    -0.07
    tone
    -0.07
     Schr
    -0.07
     خو
    -0.07
    _mov
    -0.07
     الشرقية
    -0.07
    POSITIVE LOGITS
    收益
    0.18
     लाभ
    0.16
     benefits
    0.16
    Benefits
    0.15
     benefiting
    0.15
    -benef
    0.15
     લાભ
    0.15
     benefícios
    0.14
    利益
    0.14
     Benefits
    0.14
    Activations Density 0.064%

    No Known Activations