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. 113074
    Prev
    Next
    INDEX
    Explanations

    param

    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
     PA
    -0.08
     trái
    -0.08
     unrelated
    -0.07
    חים
    -0.07
    heiro
    -0.07
     Mauritius
    -0.07
     Publisher
    -0.07
     gran
    -0.07
     kalla
    -0.07
     Gran
    -0.07
    POSITIVE LOGITS
    ised
    0.08
    �
    0.08
     plur
    0.08
    鞋
    0.08
    式
    0.08
    izations
    0.08
    stk
    0.07
    werk
    0.07
    .Offset
    0.07
     dés
    0.07
    Activations Density 0.004%

    No Known Activations