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. 113001
    Prev
    Next
    INDEX
    Explanations

    crunch

    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
     contender
    -0.08
     شعار
    -0.08
     أكبر
    -0.08
     목적
    -0.08
     Director
    -0.07
    冠军
    -0.07
     revolving
    -0.07
    خة
    -0.07
     Reactor
    -0.07
    edian
    -0.07
    POSITIVE LOGITS
     agréable
    0.09
    Leaf
    0.08
     γίνεται
    0.08
     passiert
    0.08
     consiste
    0.08
     solide
    0.08
    わせ
    0.08
    apte
    0.07
     tasty
    0.07
     történ
    0.07
    Activations Density 0.004%

    No Known Activations