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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 58662
    Prev
    Next
    INDEX
    Explanations

    again

    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
     Great
    -0.08
    Conf
    -0.08
    т
    -0.07
     Plenty
    -0.07
    Speech
    -0.07
    Great
    -0.07
     Conf
    -0.07
    ora
    -0.07
    Sp
    -0.07
     spoken
    -0.07
    POSITIVE LOGITS
    .Button
    0.09
     비용
    0.08
    됩니다
    0.08
    โ
    0.08
     쇼
    0.08
     정보를
    0.08
    足彩
    0.08
    екса
    0.08
    การพนัน
    0.08
     schoenen
    0.08
    Activations Density 0.012%

    No Known Activations