Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11787
    Prev
    Next
    INDEX
    Explanations

    Historical texts

    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
    201
    -0.09
    .")]↵
    -0.08
    awah
    -0.08
    Recent
    -0.08
    Hmm
    -0.07
    目前
    -0.07
     Rahul
    -0.07
     ator
    -0.07
     হচ্ছে
    -0.07
     করছি
    -0.07
    POSITIVE LOGITS
     હતા
    0.12
     podían
    0.11
     كانوا
    0.11
     medieval
    0.11
     pouvait
    0.10
    vaient
    0.10
     podía
    0.10
    ിരുന്ന
    0.09
     použí
    0.09
     હતાં
    0.09
    Activations Density 0.135%

    No Known Activations