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. 97044
    Prev
    Next
    INDEX
    Explanations

    medical evaluation/diagnosis

    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
     protested
    -0.08
     παραγω
    -0.08
     slogans
    -0.08
     ανθρώ
    -0.08
     propaganda
    -0.08
     लोकप्रिय
    -0.08
     दश
    -0.07
     Perfect
    -0.07
     distributes
    -0.07
     वित
    -0.07
    POSITIVE LOGITS
     обслед
    0.21
     evaluation
    0.20
     referral
    0.19
    评
    0.19
    Referral
    0.18
     referrals
    0.18
     suspicion
    0.18
     investigação
    0.18
     Evaluation
    0.18
     diagnosis
    0.18
    Activations Density 0.066%

    No Known Activations