© 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. 11-RESID-POST-AA
    11. 31044
    Prev
    Next
    INDEX
    Explanations

    Fc receptors and antibodies

    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
     IDS
    -0.09
     denies
    -0.09
     Waiting
    -0.09
     Welcome
    -0.08
     欢
    -0.08
     navig
    -0.08
     denying
    -0.08
     брос
    -0.08
     dvd
    -0.08
     banning
    -0.08
    POSITIVE LOGITS
    肩
    0.10
     antibody
    0.08
    oglob
    0.08
     antibodies
    0.08
     shoulders
    0.08
     tails
    0.08
    াংশ
    0.08
    尾
    0.08
     prost
    0.08
     класса
    0.08
    Activations Density 0.005%

    No Known Activations