© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 26493
    Prev
    Next
    INDEX
    Explanations

    Family history

    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
     dereg
    -0.09
     regain
    -0.09
     со
    -0.08
     revista
    -0.08
     cere
    -0.08
     рейтин
    -0.08
     Stati
    -0.08
     insta
    -0.08
     Trending
    -0.08
     sv
    -0.08
    POSITIVE LOGITS
    祖
    0.13
     ancestors
    0.13
     grandma
    0.12
     ancestral
    0.11
     Grandpa
    0.11
     Grandma
    0.11
     elders
    0.11
     grandparents
    0.11
    爷
    0.10
    妈妈
    0.10
    Activations Density 0.046%

    No Known Activations