© 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. 60
    Prev
    Next
    INDEX
    Explanations

    champion

    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
    ineries
    -0.08
     самая
    -0.08
     آج
    -0.08
     zgod
    -0.08
     dy
    -0.08
     вполне
    -0.07
     nale
    -0.07
     rr
    -0.07
    perts
    -0.07
     стать
    -0.07
    POSITIVE LOGITS
     champion
    0.11
    Champion
    0.10
     champions
    0.10
    champ
    0.09
     campeón
    0.09
     Champions
    0.09
    apus
    0.08
    ampion
    0.08
    �
    0.08
     vocal
    0.08
    Activations Density 0.009%

    No Known Activations