Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 112052
    Prev
    Next
    INDEX
    Explanations

    music theory

    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
     久
    -0.10
     colossal
    -0.10
     stderr
    -0.10
     grpc
    -0.09
    ақәа
    -0.09
    াঁও
    -0.09
    沉
    -0.09
     gigantic
    -0.09
     സംഭവം
    -0.09
     Tenant
    -0.09
    POSITIVE LOGITS
     simple
    0.09
    simple
    0.08
    the
    0.08
     restrictions
    0.07
    Aut
    0.07
    pal
    0.07
     सरल
    0.07
    .simple
    0.07
    express
    0.07
    restr
    0.07
    Activations Density 0.014%

    No Known Activations