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. 49855
    Prev
    Next
    INDEX
    Explanations

    pop

    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
     Wherever
    -0.08
     Clover
    -0.08
     offerte
    -0.08
    سيل
    -0.08
     زي
    -0.07
     varied
    -0.07
     statutory
    -0.07
     sorprend
    -0.07
     davantage
    -0.07
     kib
    -0.07
    POSITIVE LOGITS
    掉
    0.10
    _assoc
    0.09
     fuels
    0.08
     Mansion
    0.08
     khỏi
    0.08
     painful
    0.08
    桂
    0.08
     convictions
    0.08
    омним
    0.07
     tumble
    0.07
    Activations Density 0.001%

    No Known Activations