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. 111613
    Prev
    Next
    INDEX
    Explanations

    Reducing waste

    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
     salvation
    -0.08
    Bent
    -0.08
     petr
    -0.08
     Aman
    -0.07
     происходит
    -0.07
     Cartesian
    -0.07
     பின்ன
    -0.07
     amd
    -0.07
     làm
    -0.07
     Grave
    -0.07
    POSITIVE LOGITS
     stocked
    0.10
     מראש
    0.10
    ไว้
    0.09
     रखें
    0.09
     hazır
    0.09
     рукой
    0.09
     geregeld
    0.09
     항상
    0.09
     READY
    0.08
     રાખ
    0.08
    Activations Density 0.031%

    No Known Activations