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. 43089
    Prev
    Next
    INDEX
    Explanations

    baby

    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
     ব্যবস্থা
    -0.08
    মূল
    -0.08
    mel
    -0.07
     ఏర్పాటు
    -0.07
    වි
    -0.07
     worthy
    -0.07
    ออนไลน์
    -0.07
     proactively
    -0.07
     Fundación
    -0.07
     сторону
    -0.07
    POSITIVE LOGITS
    蛇
    0.08
    溪
    0.08
    玉
    0.08
    幼
    0.08
     стад
    0.08
     baby
    0.08
     Baby
    0.07
     കുഞ്ഞ
    0.07
    Emp
    0.07
     Tobias
    0.07
    Activations Density 0.007%

    No Known Activations