© 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. 77902
    Prev
    Next
    INDEX
    Explanations

    10-10-10

    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
    _ROOM
    -0.08
    ぎ
    -0.08
     Consensus
    -0.07
     patienter
    -0.07
    Attendance
    -0.07
     okw
    -0.07
     stylist
    -0.07
     Obrig
    -0.07
     vagas
    -0.07
     ente
    -0.07
    POSITIVE LOGITS
     fertilizers
    0.08
     manufactured
    0.08
     commercially
    0.08
    .gnu
    0.08
     ax
    0.08
    优
    0.08
    ax
    0.08
     nutrients
    0.08
     az
    0.08
     Besonders
    0.08
    Activations Density 0.004%

    No Known Activations