Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 43363
    Prev
    Next
    INDEX
    Explanations

    fire, embers, heat

    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
    па
    -0.08
    וף
    -0.08
    זרת
    -0.08
    ска
    -0.08
     repeal
    -0.07
    פו
    -0.07
     forfait
    -0.07
    ுச்
    -0.07
    代理
    -0.07
    択
    -0.07
    POSITIVE LOGITS
     lento
    0.10
     remnants
    0.09
    먼
    0.08
    岁
    0.08
     quieter
    0.08
    _WRITE
    0.08
     vibr
    0.08
    ibbons
    0.08
    nx
    0.08
     tired
    0.08
    Activations Density 0.002%

    No Known Activations