© 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. 23-RESID-POST-AA
    11. 5750
    Prev
    Next
    INDEX
    Explanations

    quotation mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pprint
    -0.09
    oces
    -0.09
    encji
    -0.08
     વેપ
    -0.08
    itivity
    -0.08
    ipr
    -0.08
     ઝડપી
    -0.08
    oción
    -0.08
    brightness
    -0.07
    부분
    -0.07
    POSITIVE LOGITS
    名無しさん
    0.10
    Saya
    0.10
    赌博
    0.09
    名無し
    0.08
    El
    0.08
    ст
    0.08
    骚
    0.08
    死亡
    0.08
    �
    0.08
    自慰
    0.08
    Activations Density 0.004%

    No Known Activations