© 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. 78020
    Prev
    Next
    INDEX
    Explanations

    TEXT and String datatypes

    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
     Slav
    -0.07
     divertir
    -0.07
     edging
    -0.07
     tarifas
    -0.07
    evaluation
    -0.07
    gi
    -0.07
    fel
    -0.07
    ombi
    -0.07
    cision
    -0.07
     SIG
    -0.07
    POSITIVE LOGITS
     remet
    0.09
    ，以及
    0.09
     และ
    0.08
    및
    0.08
     있으며
    0.08
    ോയ
    0.08
     IMPLIED
    0.08
     এবং
    0.08
     ack
    0.08
     ಮತ್ತು
    0.08
    Activations Density 0.008%

    No Known Activations