© 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. 64430
    Prev
    Next
    INDEX
    Explanations

    Engineering

    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
     maternity
    -0.08
     matern
    -0.08
     insects
    -0.08
     maternal
    -0.08
     childbirth
    -0.07
     enacted
    -0.07
     sans
    -0.07
     implemented
    -0.07
     constituted
    -0.07
    _ld
    -0.07
    POSITIVE LOGITS
    .cp
    0.09
     CPA
    0.08
    asional
    0.08
     Owner
    0.08
     esprit
    0.08
     ನಾಯಕ
    0.08
     CEO
    0.07
    castle
    0.07
     Chevrolet
    0.07
    ಾರ್
    0.07
    Activations Density 0.001%

    No Known Activations