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. 120418
    Prev
    Next
    INDEX
    Explanations

    articles

    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
     yesterday
    -0.09
     gestern
    -0.09
     вчера
    -0.09
     Corea
    -0.08
    昨天
    -0.08
    ktime
    -0.08
     rutina
    -0.08
    昨日
    -0.08
    北京时间
    -0.08
     ayer
    -0.08
    POSITIVE LOGITS
    अ
    0.08
    олож
    0.08
     Suppose
    0.07
     linear
    0.07
     spirit
    0.07
    .Ass
    0.07
     fraction
    0.07
    इसके
    0.07
    আর
    0.07
    ilename
    0.07
    Activations Density 0.009%

    No Known Activations