© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 65418
    Prev
    Next
    INDEX
    Explanations

    disk encryption

    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
    ندن
    -0.09
     arrivé
    -0.09
    ланып
    -0.09
    নীত
    -0.08
    pmn
    -0.08
    лан
    -0.08
     arrivée
    -0.08
    лал
    -0.08
    olloin
    -0.08
    حمة
    -0.08
    POSITIVE LOGITS
     masker
    0.08
     predator
    0.08
     disguise
    0.08
     guise
    0.08
     encrypted
    0.08
     mount
    0.07
     disguised
    0.07
     ciò
    0.07
     segment
    0.07
     ____
    0.07
    Activations Density 0.004%

    No Known Activations