© 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. 12797
    Prev
    Next
    INDEX
    Explanations

    阴

    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
     Wo
    -0.08
    imoine
    -0.07
     welfare
    -0.07
     silica
    -0.07
     Kum
    -0.07
    chol
    -0.07
    ponses
    -0.07
     Mora
    -0.07
    =res
    -0.07
     Mori
    -0.07
    POSITIVE LOGITS
    �
    0.08
     sat
    0.08
    FE
    0.07
     vit
    0.07
     genu
    0.07
    涨
    0.07
     gastrointestinal
    0.07
     atraves
    0.07
     crude
    0.07
     binge
    0.07
    Activations Density 0.001%

    No Known Activations