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. 49402
    Prev
    Next
    INDEX
    Explanations

    .api

    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
     вуз
    -0.09
     Villas
    -0.08
     attic
    -0.08
     rubric
    -0.07
     pequ
    -0.07
     अभ
    -0.07
     sores
    -0.07
     term
    -0.07
    ווים
    -0.07
     Terms
    -0.07
    POSITIVE LOGITS
    初始化
    0.10
    .Enable
    0.09
    .initialize
    0.09
     初始化
    0.09
     ప్రకట
    0.09
     globally
    0.09
    .configure
    0.09
    .disable
    0.09
    _Enable
    0.09
    _Init
    0.09
    Activations Density 0.023%

    No Known Activations