© 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. 11-RESID-POST-AA
    6. 44370
    Prev
    Next
    INDEX
    Explanations

    scores

    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
     Mang
    -0.09
    uy
    -0.08
     Mango
    -0.08
     esmal
    -0.08
     jackson
    -0.08
     Kek
    -0.07
     Mh
    -0.07
     Moj
    -0.07
     Mali
    -0.07
    irp
    -0.07
    POSITIVE LOGITS
     وغيره
    0.08
    WS
    0.08
    -enabled
    0.07
     والص
    0.07
     welcher
    0.07
    fec
    0.07
    Collateral
    0.07
    Ladies
    0.07
    _fee
    0.07
     stellar
    0.07
    Activations Density 0.080%

    No Known Activations