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. 42504
    Prev
    Next
    INDEX
    Explanations

    Text analysis/content creation

    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
     weaving
    -0.08
     woven
    -0.08
     tui
    -0.08
    -course
    -0.08
     Edmund
    -0.07
     Beginners
    -0.07
     Course
    -0.07
     Batt
    -0.07
    etaan
    -0.07
     novices
    -0.07
    POSITIVE LOGITS
    ส่ง
    0.08
     opportunity
    0.08
    领奖
    0.08
    불
    0.08
    வ
    0.08
    тым
    0.08
    .processor
    0.08
     Liverpool
    0.08
     defendant
    0.07
    лес
    0.07
    Activations Density 0.000%

    No Known Activations