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. 76015
    Prev
    Next
    INDEX
    Explanations

    arrows/dashes

    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
     dział
    -0.08
    Ү
    -0.08
     Vivo
    -0.08
    ுறை
    -0.08
     Büyük
    -0.07
    ஒர
    -0.07
    _ori
    -0.07
     Straw
    -0.07
    קי
    -0.07
    Buy
    -0.07
    POSITIVE LOGITS
     followed
    0.08
    amily
    0.08
       
    0.07
     fosse
    0.07
    cor
    0.07
    .cor
    0.07
     दु
    0.07
     ...,
    0.07
     antar
    0.07
    0.07
    Activations Density 0.026%

    No Known Activations