Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 117491
    Prev
    Next
    INDEX
    Explanations

    chosen

    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
     мел
    -0.08
    ত
    -0.07
    Nathan
    -0.07
    orre
    -0.07
    Computer
    -0.07
     коррект
    -0.07
    Wan
    -0.07
     максимально
    -0.07
     руш
    -0.07
    Stops
    -0.07
    POSITIVE LOGITS
     unlucky
    0.08
     Lucky
    0.08
    ेदारी
    0.08
     Birthday
    0.08
     فرصة
    0.08
     especiales
    0.08
    ेदार
    0.08
     Extraordinary
    0.08
     طويل
    0.08
    	BIT
    0.08
    Activations Density 0.006%

    No Known Activations