© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 6299
    Prev
    Next
    INDEX
    Explanations

    ś

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ascend
    -0.08
    幸
    -0.08
     umb
    -0.08
     tím
    -0.07
     присутств
    -0.07
     тун
    -0.07
     долгов
    -0.07
     этих
    -0.07
    ికార
    -0.07
     asc
    -0.07
    POSITIVE LOGITS
    608
    0.08
    سې
    0.08
    976
    0.08
     Attractions
    0.08
    605
    0.08
    RECT
    0.08
    .ALIGN
    0.08
    598
    0.08
    607
    0.08
    cff
    0.08
    Activations Density 0.001%

    No Known Activations