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. 55913
    Prev
    Next
    INDEX
    Explanations

    pull to refresh

    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
     nemet
    -0.08
    ]])
    -0.08
     Vega
    -0.08
     الحض
    -0.08
     caste
    -0.08
     odv
    -0.08
     окруж
    -0.07
                            ↵
    -0.07
     পথে
    -0.07
                           ↵
    -0.07
    POSITIVE LOGITS
    _BUFFER
    0.09
     refreshing
    0.09
    刷
    0.09
     rejuven
    0.09
    Refreshing
    0.09
    刷新
    0.08
     invigor
    0.08
    green
    0.08
    LEVEL
    0.08
     biologique
    0.08
    Activations Density 0.001%

    No Known Activations