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. 76323
    Prev
    Next
    INDEX
    Explanations

    Questions and answers

    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
     Whatever
    -0.10
     whatever
    -0.10
     allerlei
    -0.10
     messy
    -0.09
    Whatever
    -0.09
     ~~
    -0.08
     inso
    -0.08
     noix
    -0.08
    chia
    -0.08
     persoane
    -0.08
    POSITIVE LOGITS
     _____
    0.11
     __________
    0.10
     ______
    0.09
    ՞
    0.09
    ________
    0.09
     ____
    0.09
    _____
    0.08
    _______
    0.08
    ٌ
    0.08
     Bahrain
    0.08
    Activations Density 0.027%

    No Known Activations