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. 88167
    Prev
    Next
    INDEX
    Explanations

    time

    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
    �
    -0.09
     elsif
    -0.08
     colorectal
    -0.08
     tall
    -0.08
     interception
    -0.08
     Turbo
    -0.08
     elseif
    -0.07
     Granny
    -0.07
     petty
    -0.07
    Rb
    -0.07
    POSITIVE LOGITS
    一下
    0.10
     Сейчас
    0.08
     intros
    0.08
     pausa
    0.08
     آرام
    0.07
     saib
    0.07
     incubation
    0.07
     السوق
    0.07
     setmana
    0.07
     البشرية
    0.07
    Activations Density 0.029%

    No Known Activations