© 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. 3161
    Prev
    Next
    INDEX
    Explanations

    backslash

    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
    רץ
    -0.09
     Sauer
    -0.08
     দিয়ে
    -0.08
     хабар
    -0.08
     새
    -0.08
     Holm
    -0.07
     فترة
    -0.07
    imum
    -0.07
     homepage
    -0.07
     퍼
    -0.07
    POSITIVE LOGITS
    DG
    0.08
    lem
    0.07
    sun
    0.07
     rooms
    0.07
     Roosevelt
    0.07
    �
    0.07
    places
    0.07
    луч
    0.06
     antagonist
    0.06
    0.06
    Activations Density 0.002%
    No Known Activations