© 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. 64857
    Prev
    Next
    INDEX
    Explanations

    legal actions

    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
    ഗ
    -0.09
     hong
    -0.08
    onos
    -0.08
    775
    -0.07
     тун
    -0.07
     Wonderland
    -0.07
     cur
    -0.07
     tether
    -0.07
     rebel
    -0.07
    ↵   ↵
    -0.07
    POSITIVE LOGITS
     empreendimento
    0.09
     clauses
    0.08
     शुरू
    0.08
    诉
    0.08
     clause
    0.08
     iniciado
    0.08
     lawsuits
    0.08
    Título
    0.08
     τί
    0.08
     prazo
    0.08
    Activations Density 0.023%

    No Known Activations