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. 15-RESID-POST-AA
    6. 44
    Prev
    Next
    INDEX
    Explanations

    Like terms in equations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     this
    -0.08
    :↵↵
    -0.08
     lbl
    -0.07
     it
    -0.07
     other
    -0.07
    ,例如
    -0.07
     rather
    -0.07
    wner
    -0.07
    i
    -0.07
     abst
    -0.07
    POSITIVE LOGITS
    �្ន
    0.10
     ವಾರ್ತೆ
    0.10
     jedna
    0.10
     gelezen
    0.09
    հարկե
    0.09
     مليار
    0.09
    ห่ง
    0.09
     οποίος
    0.09
    മ്മദ്
    0.09
    երթ
    0.09
    Activations Density 0.006%

    No Known Activations