© 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. 2632
    Prev
    Next
    INDEX
    Explanations

    ry

    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
     nhau
    -0.08
    neud
    -0.08
    cam
    -0.08
     agility
    -0.08
    _cam
    -0.08
    ”，“
    -0.07
     scam
    -0.07
     caring
    -0.07
     adaptability
    -0.07
    acons
    -0.07
    POSITIVE LOGITS
     Dorn
    0.08
     hangs
    0.08
     Hanging
    0.08
     Sino
    0.08
     mekan
    0.07
    官方网址
    0.07
     CERN
    0.07
     때문에
    0.07
    0.07
     fumes
    0.07
    Activations Density 0.002%

    No Known Activations