© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 880
    Prev
    Next
    INDEX
    Explanations

    ahead

    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
    Ids
    -0.09
    购
    -0.09
    Episodes
    -0.08
    .Sprite
    -0.08
     Episodes
    -0.08
    Repair
    -0.08
     degrading
    -0.08
     pellets
    -0.08
    .Optional
    -0.08
    yv
    -0.08
    POSITIVE LOGITS
     GMT
    0.10
    北京时间
    0.09
     UTC
    0.09
     timezone
    0.09
    GMT
    0.09
     sister
    0.08
    0.08
     kano
    0.08
     adel
    0.08
     inland
    0.08
    Activations Density 0.026%
    No Known Activations