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. 15-RESID-POST-AA
    6. 19352
    Prev
    Next
    INDEX
    Explanations

    let

    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
    /C
    -0.07
    os
    -0.07
    /bootstrap
    -0.07
    /ne
    -0.07
     continually
    -0.07
    da
    -0.06
     significant
    -0.06
     ne
    -0.06
     ad
    -0.06
    cent
    -0.06
    POSITIVE LOGITS
     denote
    0.14
     denotes
    0.12
    未知
    0.11
     변수
    0.10
     ozna
    0.10
     variables
    0.10
     обознач
    0.10
     onbek
    0.10
     nennen
    0.10
    ชื่อ
    0.09
    Activations Density 0.050%

    No Known Activations