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. 9202
    Prev
    Next
    INDEX
    Explanations

    Email address encoding

    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
    .Connect
    -0.08
     cruise
    -0.08
     grace
    -0.08
     sentencia
    -0.07
     utility
    -0.07
     Cruise
    -0.07
    .ERROR
    -0.07
     luggage
    -0.07
     ઝડપ
    -0.07
     shear
    -0.07
    POSITIVE LOGITS
    fusc
    0.10
     thwart
    0.09
     entfernen
    0.09
    稍
    0.09
     deter
    0.09
     azalt
    0.09
     제거
    0.09
     ligeramente
    0.09
    :disable
    0.08
     ileg
    0.08
    Activations Density 0.004%

    No Known Activations