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

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 98033
    Prev
    Next
    INDEX
    Explanations

    instance

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Segoe
    -0.07
    engah
    -0.07
    letcher
    -0.07
     techo
    -0.07
    ERRQ
    -0.07
     أه
    -0.07
    ريقية
    -0.07
    277
    -0.06
     étr
    -0.06
    PRECATED
    -0.06
    POSITIVE LOGITS
     instance
    0.69
    instance
    0.66
    _instance
    0.65
    Instance
    0.64
    实例
    0.64
    	instance
    0.64
     instancia
    0.63
     Instance
    0.62
     instances
    0.61
    -instance
    0.60
    Activations Density 0.098%

    No Known Activations