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

    Neuronpedia

    Jacobian LensNEW
    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. 69578
    Prev
    Next
    INDEX
    Explanations

    lateral

    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
     especialistas
    -0.09
     legislators
    -0.09
     CEOs
    -0.09
     IPC
    -0.08
     Titans
    -0.08
     acteurs
    -0.08
     commodities
    -0.08
     Rhodes
    -0.08
     programmers
    -0.08
     userid
    -0.08
    POSITIVE LOGITS
    面积
    0.11
     cylindrical
    0.10
     펼
    0.10
    Area
    0.10
    PV
    0.09
     circumference
    0.09
     consist
    0.09
    _area
    0.09
     area
    0.09
    -area
    0.08
    Activations Density 0.005%

    No Known Activations