© 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. 1085
    Prev
    Next
    INDEX
    Explanations

    Resources and roles

    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
    杭
    -0.08
    穆
    -0.08
     squeez
    -0.07
          ↵
    -0.07
     Ode
    -0.07
     Tala
    -0.07
    �
    -0.07
     tarpe
    -0.07
     Sultan
    -0.07
     ચાર
    -0.07
    POSITIVE LOGITS
    Residence
    0.08
     UK
    0.08
     CCS
    0.07
    _cur
    0.07
     Adolesc
    0.07
     Cig
    0.07
     ред
    0.07
     নেত
    0.07
     �
    0.07
     Cof
    0.07
    Activations Density 1.470%

    No Known Activations