© 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. 25092
    Prev
    Next
    INDEX
    Explanations

    grants

    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
    Pinned
    -0.08
    edido
    -0.08
     intellig
    -0.08
     회
    -0.08
    ృష్ట
    -0.08
    initialized
    -0.07
    @Table
    -0.07
    imens
    -0.07
     genaue
    -0.07
     интел
    -0.07
    POSITIVE LOGITS
     opportunities
    0.11
     Opportunities
    0.10
     अवसर
    0.10
     prestigious
    0.10
     competitions
    0.09
     oportunidades
    0.09
     темат
    0.09
     bulletin
    0.09
     concours
    0.09
     конкурса
    0.09
    Activations Density 0.055%

    No Known Activations