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. 12850
    Prev
    Next
    INDEX
    Explanations

    Subheadings and sections

    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
     hoffen
    -0.09
     chats
    -0.08
     hoffe
    -0.08
    .List
    -0.08
     versuchen
    -0.07
    list
    -0.07
     kämpfen
    -0.07
    acts
    -0.07
    Checklist
    -0.07
    ladı
    -0.07
    POSITIVE LOGITS
     titled
    0.11
    标题
    0.10
     titulo
    0.10
     título
    0.10
     naslov
    0.10
    (title
    0.09
     APA
    0.09
     title
    0.09
     subtitle
    0.09
     제목
    0.09
    Activations Density 0.025%

    No Known Activations