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. 11693
    Prev
    Next
    INDEX
    Explanations

    UPS

    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
     substr
    -0.08
     strpos
    -0.08
     bia
    -0.08
    	result
    -0.08
    joining
    -0.08
    YO
    -0.07
    ('/',
    -0.07
     пласт
    -0.07
     detectives
    -0.07
     result
    -0.07
    POSITIVE LOGITS
    أت
    0.09
     ausreich
    0.08
     বি
    0.08
     emergency
    0.08
     secours
    0.08
     stabilized
    0.08
     sukk
    0.08
     sichern
    0.08
     automatisch
    0.08
    uken
    0.07
    Activations Density 0.003%

    No Known Activations