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. 29843
    Prev
    Next
    INDEX
    Explanations

    Link

    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
     statue
    -0.08
     普
    -0.08
     Brand
    -0.08
    featured
    -0.07
     monument
    -0.07
    Featured
    -0.07
    ワ
    -0.07
    ាត់
    -0.07
    blings
    -0.07
     muted
    -0.07
    POSITIVE LOGITS
    -level
    0.11
    层
    0.11
     স্ত
    0.10
     layer
    0.10
     स्तर
    0.10
     Layer
    0.10
    _layer
    0.09
     பகுதியில்
    0.09
    -layer
    0.09
    ရေး
    0.09
    Activations Density 0.003%

    No Known Activations