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. 102966
    Prev
    Next
    INDEX
    Explanations

    subtle hints

    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
    ​
    -0.08
    lol
    -0.08
    ​​
    -0.07
    ਠ
    -0.07
    wise
    -0.07
    。因此
    -0.07
     делу
    -0.07
    -0.07
    
    -0.07
    Integer
    -0.07
    POSITIVE LOGITS
     Wärme
    0.09
     lastly
    0.09
     pastel
    0.09
     बारिश
    0.09
     humid
    0.09
     ambiente
    0.09
     কি
    0.08
     ambiental
    0.08
     ambient
    0.08
     Чер
    0.08
    Activations Density 0.009%

    No Known Activations