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. 43581
    Prev
    Next
    INDEX
    Explanations

    flag

    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
     versatility
    -0.08
    итесь
    -0.08
     Пра
    -0.07
     практи
    -0.07
     recycl
    -0.07
     practices
    -0.07
     pratiques
    -0.07
    (vertical
    -0.07
     avoided
    -0.07
    เว
    -0.07
    POSITIVE LOGITS
     getopt
    0.09
     pomocą
    0.08
     odk
    0.08
     लो
    0.08
    -la
    0.08
    _setopt
    0.08
    	parser
    0.08
     userid
    0.08
     zg
    0.08
     XK
    0.08
    Activations Density 0.002%

    No Known Activations