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. 30022
    Prev
    Next
    INDEX
    Explanations

    ennial

    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
     BUT
    -0.08
    .rot
    -0.08
     بها
    -0.07
     mout
    -0.07
    栏
    -0.07
    alité
    -0.07
    ption
    -0.07
     زبان
    -0.07
    verst
    -0.07
    leistung
    -0.07
    POSITIVE LOGITS
    -era
    0.12
     Millennials
    0.09
     millennials
    0.09
     эпох
    0.09
    发展的
    0.08
    -friendly
    0.08
    以来
    0.08
    -sized
    0.08
     paycheck
    0.08
     Angehör
    0.08
    Activations Density 0.004%

    No Known Activations