Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 45206
    Prev
    Next
    INDEX
    Explanations

    Marcel Duchamp's "Fountain"

    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
     Chakra
    -0.08
     Buffett
    -0.08
    影
    -0.08
    传
    -0.08
    awarkan
    -0.08
    .Cells
    -0.08
     truyền
    -0.08
    usunda
    -0.07
     teint
    -0.07
    傳
    -0.07
    POSITIVE LOGITS
     plag
    0.10
    함
    0.08
    -leg
    0.08
    Definition
    0.08
    편
    0.08
     stukken
    0.08
     lc
    0.07
    legal
    0.07
    itimate
    0.07
     kawa
    0.07
    Activations Density 0.002%

    No Known Activations