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. 90152
    Prev
    Next
    INDEX
    Explanations

    lists with numbers

    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
    .email
    -0.07
     lemonade
    -0.07
    Phrase
    -0.07
     chunks
    -0.07
    .Dependency
    -0.07
    Chunk
    -0.07
    נסה
    -0.07
    ACTION
    -0.07
    .example
    -0.07
    Witness
    -0.07
    POSITIVE LOGITS
     reproductive
    0.11
     traditionally
    0.10
     contrace
    0.09
     grave
    0.09
     perempuan
    0.09
     officially
    0.09
     genders
    0.09
     Traditionally
    0.08
     oficialmente
    0.08
     wahine
    0.08
    Activations Density 0.024%

    No Known Activations