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

    Neuronpedia

    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. 26272
    Prev
    Next
    INDEX
    Explanations

    Pets and enclosures

    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
     arah
    -0.07
     hits
    -0.07
    ঙ
    -0.07
    走势
    -0.07
    方向
    -0.07
    mọ
    -0.07
    'argent
    -0.07
    择
    -0.07
     lach
    -0.07
     yal
    -0.07
    POSITIVE LOGITS
     confines
    0.16
     confinement
    0.15
     enclosure
    0.14
     enclosing
    0.14
     confin
    0.13
     compartments
    0.13
     compartment
    0.13
     enclosed
    0.12
     cage
    0.12
     cramped
    0.12
    Activations Density 0.072%

    No Known Activations