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. 30731
    Prev
    Next
    INDEX
    Explanations

    elephant

    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
    利
    -0.08
     odre
    -0.07
     тах
    -0.07
     latina
    -0.07
     zama
    -0.07
     soc
    -0.07
     zap
    -0.07
     Mej
    -0.07
     Zap
    -0.07
    ənin
    -0.07
    POSITIVE LOGITS
     Charter
    0.09
    ível
    0.08
     बहुत
    0.08
    weg
    0.08
    Appe
    0.08
     Fleet
    0.08
     Bedien
    0.08
     Kong
    0.08
     الح
    0.07
    aww
    0.07
    Activations Density 0.004%

    No Known Activations