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. 54231
    Prev
    Next
    INDEX
    Explanations

    ,

    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
    ונ
    -0.08
     
    -0.08
     כפי
    -0.08
     (?)
    -0.08
    男子
    -0.08
    足球
    -0.08
    Wilson
    -0.08
    Hill
    -0.07
     പോലെ
    -0.07
    ראו
    -0.07
    POSITIVE LOGITS
     ilọ
    0.08
    .Ex
    0.08
     Dou
    0.08
     Database
    0.08
    etek
    0.08
    ерв
    0.08
     Pattern
    0.07
     Belt
    0.07
     Melhor
    0.07
     doble
    0.07
    Activations Density 0.261%

    No Known Activations