© 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. 108730
    Prev
    Next
    INDEX
    Explanations

    messages

    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
     producteurs
    -0.08
     voed
    -0.07
     produtt
    -0.07
     vollkommen
    -0.07
     saludables
    -0.07
     Progressive
    -0.07
     valo
    -0.07
     fuels
    -0.07
    _VAL
    -0.07
    .compat
    -0.07
    POSITIVE LOGITS
     المطلوبة
    0.11
     requested
    0.10
     literally
    0.09
     المطل
    0.09
     иг
    0.08
     misdeme
    0.08
     invis
    0.08
     escon
    0.08
    お願
    0.08
    ම්බ
    0.08
    Activations Density 0.094%

    No Known Activations