© 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. 11-RESID-POST-AA
    11. 91654
    Prev
    Next
    INDEX
    Explanations

    Circuit board pins

    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
     pushed
    -0.07
     await
    -0.07
     oran
    -0.07
     Christus
    -0.07
     strcat
    -0.07
     kingdom
    -0.07
     kerajaan
    -0.07
     kodi
    -0.07
    iku
    -0.07
     Katr
    -0.07
    POSITIVE LOGITS
     prisons
    0.08
    Inputs
    0.08
    ڏ
    0.08
    _inputs
    0.08
    _gpio
    0.08
     datas
    0.08
    စ်
    0.08
    Drain
    0.08
     patents
    0.08
    izə
    0.08
    Activations Density 0.005%

    No Known Activations