© 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. 3-RESID-POST-AA
    11. 1328
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ligue
    -0.08
     leuk
    -0.08
     tastes
    -0.08
    轴
    -0.08
     Hers
    -0.08
    elu
    -0.08
    LCD
    -0.07
     lept
    -0.07
    টা
    -0.07
     임
    -0.07
    POSITIVE LOGITS
     бывают
    0.08
    ainers
    0.08
    issä
    0.07
     vork
    0.07
     kola
    0.07
     تک
    0.07
    0.07
    Signin
    0.07
     porno
    0.07
    多年
    0.07
    Activations Density 0.136%
    No Known Activations