© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 864
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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
     அக
    -0.08
     Abram
    -0.08
     fars
    -0.08
    ೊಬ್ಬ
    -0.08
     Ash
    -0.08
     Growing
    -0.07
     harvest
    -0.07
    .har
    -0.07
     condamn
    -0.07
     Dominique
    -0.07
    POSITIVE LOGITS
    instructions
    0.09
     punctuation
    0.09
     guidelines
    0.08
    scheme
    0.08
    schema
    0.08
     schema
    0.08
    规定
    0.08
     guideline
    0.08
     scheme
    0.08
     esquema
    0.08
    Activations Density 0.002%

    No Known Activations