Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 43913
    Prev
    Next
    INDEX
    Explanations

    Legal definitions

    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
    Protected
    -0.09
     bescherm
    -0.08
     island
    -0.08
     defenders
    -0.08
     protects
    -0.08
     strand
    -0.08
     eiland
    -0.08
     islands
    -0.08
    被冻结
    -0.08
     beschermen
    -0.08
    POSITIVE LOGITS
     Ms
    0.08
     upon
    0.08
     sollic
    0.07
     desfile
    0.07
     Upon
    0.07
    мас
    0.07
     teatral
    0.07
     Movie
    0.07
     convencional
    0.07
     Ads
    0.07
    Activations Density 0.001%

    No Known Activations