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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 7-RESID-POST-AA
    11. 1345
    Prev
    Next
    INDEX
    Explanations

    Trent

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     वाहन
    -0.08
     Cushion
    -0.08
     Vehicle
    -0.07
     mg
    -0.07
    -Key
    -0.07
     نج
    -0.07
     KY
    -0.07
     crochet
    -0.07
     insol
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    0.09
    Пос
    0.09
     Пос
    0.09
     pedag
    0.08
    Sie
    0.08
    TPC
    0.08
    _batches
    0.07
    会议
    0.07
    _BEGIN
    0.07
    菜
    0.07
    Activations Density 0.001%
    No Known Activations