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. 53883
    Prev
    Next
    INDEX
    Explanations

    contracts

    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
    proto
    -0.07
     reagent
    -0.07
     rind
    -0.07
     imin
    -0.07
     toets
    -0.07
    AS
    -0.07
    IND
    -0.07
    outine
    -0.07
    ASY
    -0.07
    Iz
    -0.07
    POSITIVE LOGITS
     "...
    0.09
    	true
    0.08
     wn
    0.08
     தெரிவித்துள்ளார்
    0.08
    真实性
    0.08
     owns
    0.08
     warranties
    0.08
     CFO
    0.08
     něco
    0.08
    .wso
    0.08
    Activations Density 0.002%

    No Known Activations