© 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. 91712
    Prev
    Next
    INDEX
    Explanations

    _hint

    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
    ука
    -0.08
     camisa
    -0.08
     ceremonial
    -0.08
     justice
    -0.07
     represented
    -0.07
     Justice
    -0.07
     न्याय
    -0.07
     Academia
    -0.07
    cloth
    -0.07
    _init
    -0.07
    POSITIVE LOGITS
     ਮ
    0.08
     ਵਿਚ
    0.07
    -bike
    0.07
    0.07
     JLabel
    0.07
     partículas
    0.07
    /date
    0.07
    /DVD
    0.07
     daoine
    0.07
     particles
    0.07
    Activations Density 0.036%
    No Known Activations