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. 77246
    Prev
    Next
    INDEX
    Explanations

    poetry

    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
     Wanda
    -0.07
    يين
    -0.07
    ?,
    -0.07
    .Label
    -0.07
    Instantiation
    -0.07
    ını
    -0.07
     Scala
    -0.07
     attrib
    -0.07
    _LABEL
    -0.07
    标签
    -0.07
    POSITIVE LOGITS
     aj
    0.08
     Driven
    0.08
    �
    0.08
    Driven
    0.08
    ござ
    0.08
     chăm
    0.08
     magical
    0.08
     prazer
    0.08
     fulfilling
    0.08
     parody
    0.08
    Activations Density 0.009%

    No Known Activations