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. 43774
    Prev
    Next
    INDEX
    Explanations

    Assembly/compiled code

    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
    会员
    -0.09
     Dhabi
    -0.09
     Sitzung
    -0.09
    wives
    -0.09
    	pthread
    -0.08
    wife
    -0.08
    VIDEOS
    -0.08
    zeichnen
    -0.08
     uczest
    -0.08
    Dining
    -0.08
    POSITIVE LOGITS
    64
    0.09
    (target
    0.09
    Literal
    0.09
    Immediate
    0.09
    -target
    0.09
     target
    0.09
    (-
    0.08
     immed
    0.08
     (-
    0.08
     непосред
    0.08
    Activations Density 0.002%

    No Known Activations