Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit 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. 23-RESID-POST-AA
    6. 130774
    Prev
    Next
    INDEX
    Explanations

    Fashion accessories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     三
    -0.08
     ആറ
    -0.08
     stopping
    -0.07
    ាំង
    -0.07
     agony
    -0.07
     足球
    -0.07
     competitiveness
    -0.07
     endurance
    -0.07
     三国
    -0.07
     welfare
    -0.07
    POSITIVE LOGITS
     metallic
    0.15
    statement
    0.15
     statement
    0.15
    Statement
    0.14
     Statement
    0.14
     luxe
    0.14
     Metallic
    0.13
     gemstone
    0.12
     неож
    0.11
    (statement
    0.11
    Activations Density 0.032%

    No Known Activations