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. 60613
    Prev
    Next
    INDEX
    Explanations

    Japanese text

    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
    .observe
    -0.08
     ബാങ്ക
    -0.08
     banque
    -0.08
    .construct
    -0.08
     uninter
    -0.07
     tuned
    -0.07
     Tunes
    -0.07
     బ్య
    -0.07
     noter
    -0.07
     construct
    -0.07
    POSITIVE LOGITS
    ુંદર
    0.08
    �
    0.08
    718
    0.08
    958
    0.08
    953
    0.08
     causar
    0.07
     �
    0.07
    糕
    0.07
    357
    0.07
    уп
    0.07
    Activations Density 0.020%

    No Known Activations