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. 111974
    Prev
    Next
    INDEX
    Explanations

    IMITER

    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
     ше
    -0.09
    UM
    -0.08
     endorsed
    -0.08
     mães
    -0.08
    ုံ
    -0.08
     শৰ
    -0.08
      
    -0.07
     Mats
    -0.07
     âgées
    -0.07
    شد
    -0.07
    POSITIVE LOGITS
    Decimal
    0.08
    isson
    0.08
     permanently
    0.08
     Decimal
    0.08
     decimals
    0.08
     بندی
    0.07
     Tempor
    0.07
     temporarily
    0.07
    obals
    0.07
     decimal
    0.07
    Activations Density 0.013%

    No Known Activations