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. 12751
    Prev
    Next
    INDEX
    Explanations

    3D modeling

    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
    短信
    -0.09
     ciphertext
    -0.09
    Songs
    -0.08
    .cookies
    -0.08
     spelled
    -0.08
     blueberry
    -0.08
     blueberries
    -0.08
     diarrhea
    -0.08
     blankets
    -0.08
     Caesar
    -0.08
    POSITIVE LOGITS
     Autodesk
    0.13
     voxel
    0.11
    _pose
    0.11
    Voxel
    0.11
     spherical
    0.11
     Blender
    0.10
     viewer
    0.10
     Viewer
    0.10
     deform
    0.10
     CAD
    0.10
    Activations Density 0.041%

    No Known Activations