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. 54032
    Prev
    Next
    INDEX
    Explanations

    opposite

    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
    )&&(
    -0.08
    <{
    -0.08
    secure
    -0.08
     exemplar
    -0.08
     zunehmend
    -0.08
     secure
    -0.07
    <Login
    -0.07
    -und
    -0.07
     వివర
    -0.07
    geb
    -0.07
    POSITIVE LOGITS
     Highway
    0.08
     khỏi
    0.08
    品
    0.08
    掉
    0.08
    lies
    0.07
     Stunning
    0.07
     doos
    0.07
     zijde
    0.07
     میز
    0.07
    乡
    0.07
    Activations Density 0.012%

    No Known Activations