© 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. 63274
    Prev
    Next
    INDEX
    Explanations

    same

    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
     antecedentes
    -0.08
    /le
    -0.07
    yeah
    -0.07
    percent
    -0.07
     '',
    -0.07
    pause
    -0.07
     parlament
    -0.07
    ('/
    -0.07
    antur
    -0.07
     Leafs
    -0.07
    POSITIVE LOGITS
    Across
    0.11
    统一
    0.11
     Across
    0.10
     across
    0.10
     tegelijk
    0.10
     одинаков
    0.10
     globally
    0.10
     shared
    0.09
     condiv
    0.09
     consistently
    0.09
    Activations Density 0.038%

    No Known Activations