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. 12263
    Prev
    Next
    INDEX
    Explanations

    cooking recipes and serving instructions

    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
     rap
    -0.08
    	properties
    -0.08
     bracelets
    -0.08
    排列
    -0.08
     milion
    -0.07
    encent
    -0.07
    Pure
    -0.07
     beats
    -0.07
     Beats
    -0.07
    abang
    -0.07
    POSITIVE LOGITS
    та
    0.09
    .department
    0.08
     downtime
    0.08
     сыг
    0.07
     lug
    0.07
    .post
    0.07
    сыра
    0.07
    Printing
    0.07
    redicate
    0.07
     heir
    0.07
    Activations Density 0.006%

    No Known Activations