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. 49318
    Prev
    Next
    INDEX
    Explanations

    1

    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
     čo
    -0.09
     açıkl
    -0.08
    �
    -0.08
    gäng
    -0.08
     że
    -0.07
    اً
    -0.07
    little
    -0.07
    өм
    -0.07
    іч
    -0.07
     القدس
    -0.07
    POSITIVE LOGITS
     hinweg
    0.08
     svol
    0.08
     inclusive
    0.08
    ]={
    0.08
     inzicht
    0.08
     transit
    0.07
    0.07
    ->{
    0.07
     Rij
    0.07
     lid
    0.07
    Activations Density 0.020%

    No Known Activations