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. 49256
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    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
    @mail
    -0.08
    (pref
    -0.07
    .Info
    -0.07
     Falcon
    -0.07
    (def
    -0.07
    (window
    -0.07
    едь
    -0.07
     Prescott
    -0.07
     mets
    -0.07
    (timestamp
    -0.07
    POSITIVE LOGITS
     қис
    0.08
     лі
    0.08
    ducers
    0.08
     قليلة
    0.08
     dị
    0.08
     Outline
    0.08
     القوى
    0.08
     قى
    0.08
     BTS
    0.08
    	show
    0.08
    Activations Density 0.004%

    No Known Activations