© 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. 19-RESID-POST-AA
    11. 103217
    Prev
    Next
    INDEX
    Explanations

    description

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ngenxa
    -0.09
     обстоятель
    -0.09
     تعیین
    -0.09
     folgt
    -0.08
    ativer
    -0.08
     saboda
    -0.08
     പ്രവ
    -0.08
     בעקבות
    -0.08
     clauses
    -0.08
     negligence
    -0.08
    POSITIVE LOGITS
     description
    0.13
     descripción
    0.12
     described
    0.12
     descrição
    0.11
    description
    0.11
     describing
    0.11
     visualize
    0.11
     describe
    0.11
     descr
    0.11
    .description
    0.11
    Activations Density 0.048%

    No Known Activations