© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7436
    Prev
    Next
    INDEX
    Explanations

    Snow White

    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
     fent
    -0.09
     sampled
    -0.08
    .utcnow
    -0.08
     adrenaline
    -0.07
     inferred
    -0.07
    CUDA
    -0.07
     né
    -0.07
     opname
    -0.07
     cerebral
    -0.07
    Tran
    -0.07
    POSITIVE LOGITS
     princess
    0.14
     Princess
    0.12
    Princess
    0.12
     princes
    0.12
     enchanting
    0.12
     prince
    0.11
     enchanted
    0.11
     villagers
    0.11
     राजा
    0.11
     mythical
    0.11
    Activations Density 0.034%

    No Known Activations