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. 49286
    Prev
    Next
    INDEX
    Explanations

    numerical simulation & meshing

    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
     albums
    -0.09
     exile
    -0.08
     narciss
    -0.08
     scrolling
    -0.08
    spent
    -0.08
     skat
    -0.08
     Tinder
    -0.08
     clair
    -0.08
     arist
    -0.08
    ברות
    -0.08
    POSITIVE LOGITS
    .mesh
    0.15
    (mesh
    0.13
     mesh
    0.13
     timestep
    0.13
     meshes
    0.12
     discret
    0.12
     CFD
    0.12
    .Mesh
    0.11
     voxel
    0.11
    Mesh
    0.11
    Activations Density 0.009%

    No Known Activations