© 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. 99482
    Prev
    Next
    INDEX
    Explanations

    农

    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
     لإ
    -0.08
     Milo
    -0.08
     Jahrze
    -0.08
     implantation
    -0.07
     Зав
    -0.07
     Shelton
    -0.07
     Fah
    -0.07
     Arms
    -0.07
     Loh
    -0.07
    .cfg
    -0.07
    POSITIVE LOGITS
     powerful
    0.09
    一下
    0.08
    ਂ
    0.08
    Psi
    0.08
    ñe
    0.08
     uneven
    0.07
     underestimated
    0.07
    фф
    0.07
     logarith
    0.07
    zyć
    0.07
    Activations Density 0.000%

    No Known Activations