© 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. 3-RESID-POST-AA
    11. 2984
    Prev
    Next
    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     некалькі
    -0.09
     Rathaus
    -0.08
     ποσ
    -0.08
     ღვ
    -0.08
     пять
    -0.08
    otas
    -0.08
     мяне
    -0.08
     Série
    -0.08
     igreja
    -0.08
    асына
    -0.08
    POSITIVE LOGITS
    าก
    0.08
    ht
    0.07
    graf
    0.07
     badly
    0.07
     puzz
    0.07
    opian
    0.07
     loose
    0.07
    ::::
    0.07
    results
    0.07
    �
    0.07
    Activations Density 0.000%

    No Known Activations