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. 61080
    Prev
    Next
    INDEX
    Explanations

    maximum value

    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
     damp
    -0.09
    ovin
    -0.08
     espa
    -0.08
     visa
    -0.07
    _rad
    -0.07
     licença
    -0.07
     bırak
    -0.07
    ieerd
    -0.07
    වේ
    -0.07
    License
    -0.07
    POSITIVE LOGITS
     Maximum
    0.10
     maximizing
    0.10
     Superior
    0.09
     superior
    0.09
    Superior
    0.09
     максим
    0.09
     achievable
    0.09
     attainable
    0.09
     Optimal
    0.09
    峰
    0.08
    Activations Density 0.046%

    No Known Activations