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. 58715
    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
    場合
    -0.08
    ؟
    -0.08
     राष्ट्रपति
    -0.07
     assass
    -0.07
     deton
    -0.07
    =="
    -0.07
     dictator
    -0.07
     merkt
    -0.07
    اض
    -0.07
     detects
    -0.07
    POSITIVE LOGITS
    ைப்ப
    0.08
     vielseit
    0.08
     vielfält
    0.08
     sess
    0.07
    慎
    0.07
     redefine
    0.07
     essentials
    0.07
     versatility
    0.07
     absurd
    0.07
     Essentials
    0.07
    Activations Density 0.084%

    No Known Activations