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. 29905
    Prev
    Next
    INDEX
    Explanations

    assembly code

    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
     Biden
    -0.09
     provenance
    -0.09
     boll
    -0.08
     steak
    -0.08
     descobrir
    -0.08
     custody
    -0.08
    schaft
    -0.08
    र्च
    -0.08
     Bezos
    -0.08
     coj
    -0.08
    POSITIVE LOGITS
     trapped
    0.10
    □
    0.08
    ,T
    0.08
    :T
    0.08
     Alert
    0.08
    เข้าส
    0.08
     traps
    0.08
    alert
    0.08
    .alert
    0.08
     ويا
    0.08
    Activations Density 0.006%

    No Known Activations