© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 64268
    Prev
    Next
    INDEX
    Explanations

    legal/business disputes

    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
     conjug
    -0.09
     muu
    -0.09
    乎
    -0.09
     guid
    -0.08
     unei
    -0.08
     sinni
    -0.08
     guider
    -0.08
     esperamos
    -0.08
     GUID
    -0.08
    些什么
    -0.08
    POSITIVE LOGITS
     Orom
    0.08
    istan
    0.07
     Baru
    0.07
    -O
    0.07
     Lack
    0.07
    progress
    0.07
    陷
    0.07
     disagree
    0.07
    opening
    0.07
     нович
    0.07
    Activations Density 0.113%

    No Known Activations