© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 26429
    Prev
    Next
    INDEX
    Explanations

    Revit software

    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
     encouraged
    -0.10
     urged
    -0.09
    威
    -0.09
     awakening
    -0.09
     embarrassed
    -0.09
     empowers
    -0.08
     encouragement
    -0.08
     malad
    -0.08
     Awak
    -0.08
     confession
    -0.08
    POSITIVE LOGITS
     Fixture
    0.09
     flange
    0.09
    Workspace
    0.09
     Fixtures
    0.09
     modeling
    0.08
     Gebäude
    0.08
    dummy
    0.08
    _defined
    0.08
    CAD
    0.08
    Thickness
    0.08
    Activations Density 0.018%

    No Known Activations