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. 12842
    Prev
    Next
    INDEX
    Explanations

    tight

    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
    delay
    -0.08
     Ster
    -0.08
     latency
    -0.07
     steroid
    -0.07
     Bundes
    -0.07
     ход
    -0.07
    Lag
    -0.07
     Lag
    -0.07
     alem
    -0.07
     delays
    -0.07
    POSITIVE LOGITS
    Enough
    0.10
     tightened
    0.09
     tighter
    0.09
     πέ
    0.09
    力度
    0.09
     pearls
    0.08
     enough
    0.08
     شد
    0.08
     grip
    0.08
     grips
    0.08
    Activations Density 0.011%

    No Known Activations