© 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. 78870
    Prev
    Next
    INDEX
    Explanations

    single quotes

    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
    ovit
    -0.08
    异
    -0.08
     discret
    -0.08
    otis
    -0.08
     mig
    -0.08
    avas
    -0.07
     horas
    -0.07
     grá
    -0.07
    .Pos
    -0.07
     discre
    -0.07
    POSITIVE LOGITS
    -col
    0.08
     사용할
    0.08
     tercih
    0.08
    ewel
    0.08
     carr
    0.07
    ेड
    0.07
     대신
    0.07
    [F
    0.07
     ખુ
    0.07
    .manager
    0.07
    Activations Density 0.002%

    No Known Activations