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. 23882
    Prev
    Next
    INDEX
    Explanations

    Internal company information

    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
     Esperanto
    -0.09
    _rng
    -0.08
     Gegen
    -0.08
     Fried
    -0.08
     recogn
    -0.08
     Friedman
    -0.08
     unterwegs
    -0.08
     Espresso
    -0.08
     integer
    -0.07
     chooser
    -0.07
    POSITIVE LOGITS
    部门
    0.17
    员工
    0.16
     업무
    0.16
     직원
    0.16
     internes
    0.15
     내부
    0.15
    Employees
    0.14
     отдела
    0.14
     корпоратив
    0.14
     팀
    0.14
    Activations Density 0.219%

    No Known Activations