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. 53001
    Prev
    Next
    INDEX
    Explanations

    worry

    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
     direção
    -0.08
    त्र
    -0.08
    near
    -0.07
    510
    -0.07
    seg
    -0.07
    =text
    -0.07
     समस्य
    -0.07
    parameter
    -0.07
    Lik
    -0.07
    डी
    -0.07
    POSITIVE LOGITS
     reassure
    0.10
     reassurance
    0.10
     جات
    0.09
     reassuring
    0.09
     genu
    0.09
     اليوم
    0.08
     അമ്മ
    0.08
    journ
    0.08
     cariño
    0.08
     마음
    0.08
    Activations Density 0.005%

    No Known Activations