© 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. 7-RESID-POST-AA
    11. 1225
    Prev
    Next
    INDEX
    Explanations

    talking

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contested
    -0.08
     contests
    -0.07
     after
    -0.07
    -top
    -0.07
     contention
    -0.07
    ア
    -0.07
     Kick
    -0.07
     formation
    -0.07
     losers
    -0.07
    Kick
    -0.07
    POSITIVE LOGITS
     pierres
    0.09
     stets
    0.08
     comeback
    0.08
     মূল্য
    0.08
     byose
    0.08
     노력
    0.08
     demás
    0.08
     ఎంప
    0.08
     происход
    0.08
     చర్య
    0.08
    Activations Density 0.107%

    No Known Activations