© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 7-RESID-POST-AA
    6. 1191
    Prev
    Next
    INDEX
    Explanations

    Boolean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (debug
    -0.08
     stripe
    -0.08
    _debug
    -0.08
     Anadolu
    -0.07
    _mesh
    -0.07
     debug
    -0.07
    (Constants
    -0.07
     xem
    -0.07
    (
    -0.07
    .yy
    -0.07
    POSITIVE LOGITS
    Creator
    0.09
     Creator
    0.09
     போல
    0.09
    โน
    0.08
     conspiracy
    0.08
     bookmarking
    0.08
    arquivo
    0.08
     beg
    0.08
     Cree
    0.08
    Captor
    0.08
    Activations Density 0.001%

    No Known Activations