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. 12210
    Prev
    Next
    INDEX
    Explanations

    =

    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
    Recovered
    -0.07
    开户
    -0.07
    Recover
    -0.07
    :^{↵
    -0.07
    CSC
    -0.07
    Courses
    -0.07
     Workbook
    -0.07
    たり
    -0.07
    Called
    -0.07
    _transactions
    -0.07
    POSITIVE LOGITS
    beschreibung
    0.11
     concise
    0.10
     описание
    0.10
     detaill
    0.10
     опис
    0.10
     подробно
    0.09
     detall
    0.09
     vivid
    0.09
     বিস্তারিত
    0.09
    รายละเอียด
    0.09
    Activations Density 0.374%

    No Known Activations