© 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. 23-RESID-POST-AA
    11. 96538
    Prev
    Next
    INDEX
    Explanations

    new

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Set
    -0.13
    Map
    -0.13
    (Set
    -0.10
    Mapa
    -0.10
    Proto
    -0.10
    Standard
    -0.10
    Recursive
    -0.09
    _set
    -0.09
     Set
    -0.09
    Equip
    -0.09
    POSITIVE LOGITS
     lớn
    0.10
    ữu
    0.09
     Records
    0.09
     Albums
    0.09
     Sizes
    0.09
     الكبيرة
    0.09
    };↵↵/
    0.09
     Groups
    0.09
     Stores
    0.08
     Collections
    0.08
    Activations Density 0.001%

    No Known Activations