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. 54443
    Prev
    Next
    INDEX
    Explanations

    Spreading/distribution

    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
     FROM
    -0.08
    Blueprint
    -0.08
     stealth
    -0.08
    hosts
    -0.08
     flair
    -0.07
     flights
    -0.07
    -from
    -0.07
    films
    -0.07
     Flair
    -0.07
     flew
    -0.07
    POSITIVE LOGITS
     distributes
    0.11
     distribuir
    0.11
     répart
    0.11
     redistributed
    0.11
     verteilt
    0.11
     redistribute
    0.10
     распредел
    0.10
     Redistribution
    0.10
     distributing
    0.10
     توزيع
    0.10
    Activations Density 0.009%

    No Known Activations