© 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. 65585
    Prev
    Next
    INDEX
    Explanations

    throw

    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
     �
    -0.08
     알려
    -0.08
    护
    -0.08
    adx
    -0.08
     ndz
    -0.08
     Insets
    -0.08
     Nost
    -0.07
     postar
    -0.07
     bdsm
    -0.07
     smartphones
    -0.07
    POSITIVE LOGITS
     blonde
    0.08
    rych
    0.08
     ringan
    0.08
     fired
    0.07
     தொ
    0.07
     முட
    0.07
     எழ
    0.07
     ringing
    0.07
     माम
    0.07
     отдель
    0.07
    Activations Density 0.002%

    No Known Activations