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. 98064
    Prev
    Next
    INDEX
    Explanations

    almond

    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
     Reload
    -0.08
    istics
    -0.08
    πόν
    -0.08
     Probe
    -0.08
    ชาย
    -0.08
     Tyr
    -0.07
     Potato
    -0.07
     Kartoff
    -0.07
    ്വേഷ
    -0.07
    /XMLSchema
    -0.07
    POSITIVE LOGITS
     meal
    0.14
     milk
    0.12
    meal
    0.12
    milk
    0.12
     Joy
    0.11
     bisc
    0.11
     Meal
    0.11
     Breeze
    0.11
    Meal
    0.10
     joy
    0.10
    Activations Density 0.002%

    No Known Activations