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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 111543
    Prev
    Next
    INDEX
    Explanations

    massage

    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
     civilizations
    -0.09
    эры
    -0.08
     civilization
    -0.08
    zki
    -0.08
     prestig
    -0.08
    spath
    -0.08
     Kush
    -0.07
    .instances
    -0.07
    arren
    -0.07
     Bung
    -0.07
    POSITIVE LOGITS
    按摩
    0.10
    otherapeut
    0.10
     therapist
    0.10
    otherapy
    0.09
     therapy
    0.09
    се
    0.09
     remission
    0.08
     Oils
    0.08
     Kana
    0.08
     horm
    0.08
    Activations Density 0.005%

    No Known Activations