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. 78731
    Prev
    Next
    INDEX
    Explanations

    math equations

    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
     formatted
    -0.10
    Formatted
    -0.08
     formatter
    -0.08
     formatting
    -0.08
    Formatting
    -0.08
    _t
    -0.07
    _diff
    -0.07
    00
    -0.07
     mafia
    -0.07
    Mixer
    -0.07
    POSITIVE LOGITS
     Checking
    0.09
     өг
    0.09
     eku
    0.09
     soq
    0.08
     allein
    0.08
     ಬಿಜೆ
    0.08
     heredit
    0.08
     Aussage
    0.08
     dargestellt
    0.08
     кыр
    0.08
    Activations Density 0.029%

    No Known Activations