© 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. 114116
    Prev
    Next
    INDEX
    Explanations

    not

    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
    (comp
    -0.09
    'ess
    -0.09
    comp
    -0.08
    _rgctx
    -0.08
     Comp
    -0.08
    (J
    -0.08
     mai
    -0.08
     Issue
    -0.08
    ainen
    -0.08
    orset
    -0.08
    POSITIVE LOGITS
     کف
    0.08
     esf
    0.08
     decks
    0.07
    артам
    0.07
     commute
    0.07
     கார
    0.07
    ej
    0.07
    zum
    0.07
     seng
    0.07
     ej
    0.07
    Activations Density 0.137%

    No Known Activations