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. 105972
    Prev
    Next
    INDEX
    Explanations

    the

    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
    人在
    -0.09
    ussu
    -0.07
     entail
    -0.07
     composer
    -0.07
     exposing
    -0.07
    Ios
    -0.07
     whereas
    -0.07
    hando
    -0.07
    ఎ
    -0.07
    Ie
    -0.07
    POSITIVE LOGITS
     chilly
    0.10
     Camp
    0.09
    roffen
    0.08
     kitty
    0.08
     Wonderland
    0.08
     ohnehin
    0.08
     tous
    0.08
     woo
    0.08
     prostoru
    0.08
    _defs
    0.08
    Activations Density 0.083%

    No Known Activations