© 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. 94499
    Prev
    Next
    INDEX
    Explanations

    east/west regions

    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
     beschermd
    -0.07
     Texas
    -0.07
     Manchester
    -0.07
    Bitmap
    -0.07
    .Inner
    -0.07
     properties
    -0.07
    =true
    -0.07
    .bitmap
    -0.07
    rx
    -0.06
     pels
    -0.06
    POSITIVE LOGITS
    ај
    0.09
     Som
    0.09
    흥
    0.08
    愿
    0.08
     ikkje
    0.08
     đôi
    0.08
     maggiore
    0.08
     resignation
    0.08
     الطلب
    0.08
     нема
    0.08
    Activations Density 0.007%

    No Known Activations