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

    Neuronpedia

    APICircuit 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. 58604
    Prev
    Next
    INDEX
    Explanations

    Questions and sentences

    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
     paw
    -0.10
     coveted
    -0.09
    щик
    -0.08
    щики
    -0.08
    Chevron
    -0.08
     rebellion
    -0.08
     ż
    -0.07
    -chevron
    -0.07
     loyal
    -0.07
     ausgel
    -0.07
    POSITIVE LOGITS
    _excerpt
    0.11
     sentences
    0.11
     phrases
    0.11
    摘要
    0.10
     excerpts
    0.10
    长度
    0.10
    一句
    0.10
    _sentence
    0.09
     headlines
    0.09
     বাক
    0.09
    Activations Density 0.010%

    No Known Activations