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. 77303
    Prev
    Next
    INDEX
    Explanations

    wrapped/wrapping

    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
     katk
    -0.09
     equilibr
    -0.09
     equilibrium
    -0.08
     vzh
    -0.08
    ாங்க
    -0.08
     ega
    -0.07
    browse
    -0.07
     puh
    -0.07
     pelik
    -0.07
    Counters
    -0.07
    POSITIVE LOGITS
    围
    0.10
    绕
    0.10
    关于
    0.09
    Around
    0.09
    around
    0.09
    -around
    0.09
     torno
    0.09
     Around
    0.09
     around
    0.08
     包
    0.08
    Activations Density 0.009%

    No Known Activations