Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54264
    Prev
    Next
    INDEX
    Explanations

    而

    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
     samp
    -0.08
     Luna
    -0.08
     Akk
    -0.07
    (B
    -0.07
    imu
    -0.07
     Heal
    -0.07
     calculation
    -0.07
     wedge
    -0.07
     dum
    -0.07
     kust
    -0.07
    POSITIVE LOGITS
    且
    0.09
    不是
    0.09
     airborne
    0.08
     tug
    0.08
     adm
    0.08
     동시에
    0.08
     respecto
    0.08
     wholes
    0.08
     Ci
    0.07
     overse
    0.07
    Activations Density 0.004%

    No Known Activations