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. 88083
    Prev
    Next
    INDEX
    Explanations

    &

    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
    	div
    -0.08
     ngen
    -0.08
     lada
    -0.08
    .Up
    -0.08
     losses
    -0.08
    ässig
    -0.08
     constituted
    -0.08
     afili
    -0.07
     wear
    -0.07
     føler
    -0.07
    POSITIVE LOGITS
     আ
    0.08
     পাওয়া
    0.08
    Student
    0.08
     Ced
    0.07
    Posts
    0.07
     રોક
    0.07
     Papier
    0.07
    നം
    0.07
    Nie
    0.07
    Projects
    0.07
    Activations Density 0.002%

    No Known Activations