Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 74987
    Prev
    Next
    INDEX
    Explanations

    Code with loops/indexing

    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
    aknya
    -0.08
     iki
    -0.07
    VR
    -0.07
     Office
    -0.07
     Baş
    -0.07
     cock
    -0.07
    anı
    -0.07
    office
    -0.07
    idel
    -0.07
     Victorian
    -0.07
    POSITIVE LOGITS
     zach
    0.08
    鱼儿
    0.08
     beh
    0.08
     菲
    0.08
     duk
    0.07
     ys
    0.07
    веч
    0.07
     Typ
    0.07
    Caught
    0.07
     слуш
    0.07
    Activations Density 0.003%

    No Known Activations