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. 102854
    Prev
    Next
    INDEX
    Explanations

    Windows socket programming

    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
    лев
    -0.08
    ộ
    -0.08
    мов
    -0.07
    虑
    -0.07
    目前
    -0.07
     assuming
    -0.07
    ത്തിന്റെ
    -0.07
    මේ
    -0.07
    lež
    -0.07
    機
    -0.07
    POSITIVE LOGITS
     benötigen
    0.09
    xhr
    0.09
     XMLHttp
    0.09
     htons
    0.09
     interchangeable
    0.09
     potrebno
    0.09
     necess
    0.09
    xdc
    0.09
     braucht
    0.09
     requerida
    0.08
    Activations Density 0.002%

    No Known Activations