© 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. 5705
    Prev
    Next
    INDEX
    Explanations

    say "from"

    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
     provenant
    -0.18
     originating
    -0.17
     provenientes
    -0.16
     derived
    -0.15
     afkomstig
    -0.14
    derived
    -0.14
     venant
    -0.14
     berasal
    -0.14
     desde
    -0.14
     vanuit
    -0.13
    POSITIVE LOGITS
     عن
    0.17
     khỏi
    0.13
     عنه
    0.12
     form
    0.12
     عنها
    0.11
    于
    0.10
    form
    0.10
    <form
    0.10
    عن
    0.10
     fom
    0.09
    Activations Density 0.071%

    No Known Activations