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. 12495
    Prev
    Next
    INDEX
    Explanations

    Weighing

    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
     تولید
    -0.07
     prevent
    -0.07
    award
    -0.07
    주의
    -0.07
     contributing
    -0.07
     سرمایه
    -0.07
     personnelle
    -0.07
     multicultural
    -0.07
    corpor
    -0.07
     Firmen
    -0.07
    POSITIVE LOGITS
     precar
    0.08
    巧
    0.08
     apparatus
    0.08
     drums
    0.08
     amach
    0.08
     Setup
    0.08
    weg
    0.07
    .Setup
    0.07
     DUT
    0.07
     rud
    0.07
    Activations Density 0.003%

    No Known Activations