© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 7796
    Prev
    Next
    INDEX
    Explanations

    measurements and precision

    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
    fidh
    -0.08
     jedhu
    -0.08
     Nye
    -0.08
     fis
    -0.08
     Devin
    -0.08
    tingen
    -0.08
     vigente
    -0.08
     Brie
    -0.07
    _buff
    -0.07
     skier
    -0.07
    POSITIVE LOGITS
     precision
    0.14
     gran
    0.13
    Precision
    0.13
     Precision
    0.13
    precision
    0.12
     finer
    0.12
     precisão
    0.11
    精准
    0.11
     precisión
    0.11
     accuracy
    0.11
    Activations Density 0.016%

    No Known Activations