© 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. 30887
    Prev
    Next
    INDEX
    Explanations

    formed

    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
     optimism
    -0.08
    Af
    -0.08
     paced
    -0.08
    home
    -0.08
     режим
    -0.08
    helle
    -0.08
    grpc
    -0.08
     വൈക
    -0.08
     terbaru
    -0.07
    respons
    -0.07
    POSITIVE LOGITS
    টির
    0.09
    গুল
    0.08
     wen
    0.07
     обстоятель
    0.07
    �
    0.07
     circumstances
    0.07
     вокруг
    0.07
     المع
    0.07
    两个
    0.07
    LLU
    0.07
    Activations Density 0.008%

    No Known Activations