© 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. 23-RESID-POST-AA
    11. 47618
    Prev
    Next
    INDEX
    Explanations

    computer

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hormona
    -0.08
     hormon
    -0.08
     сән
    -0.07
     mediterr
    -0.07
     Marley
    -0.07
     Evangel
    -0.07
     התר
    -0.07
     Legislativo
    -0.07
     hormonal
    -0.07
     lyrical
    -0.07
    POSITIVE LOGITS
     computer
    0.62
     computadora
    0.58
     computador
    0.58
     komputer
    0.57
     computers
    0.56
     Computer
    0.56
    Computer
    0.56
    computer
    0.56
    电脑
    0.56
     компьют
    0.56
    Activations Density 0.126%

    No Known Activations