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. 23-RESID-POST-AA
    6. 98519
    Prev
    Next
    INDEX
    Explanations

    say "each"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Individual
    -0.12
    Individual
    -0.11
    individual
    -0.10
     Every
    -0.10
     individuele
    -0.10
    every
    -0.10
     individuell
    -0.09
     individuel
    -0.09
     individual
    -0.09
    Every
    -0.09
    POSITIVE LOGITS
     서로
    0.32
     birbir
    0.30
    彼
    0.29
     elkaar
    0.27
     друг
    0.26
    einander
    0.26
     nhau
    0.25
     miteinander
    0.25
     തമ്മ
    0.25
     gegense
    0.22
    Activations Density 0.059%

    No Known Activations