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. 23-RESID-POST-AA
    6. 130935
    Prev
    Next
    INDEX
    Explanations

    90

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    15
    -0.10
    ১৫
    -0.10
    १५
    -0.08
    半
    -0.08
    15
    -0.08
    -0.08
    ۱۵
    -0.08
     scorer
    -0.08
    30
    -0.07
    ३०
    -0.07
    POSITIVE LOGITS
    75
    0.11
    ९
    0.10
    90
    0.10
    ৯
    0.10
     septembre
    0.10
     September
    0.09
    September
    0.09
     septiembre
    0.09
     podat
    0.09
     estruct
    0.09
    Activations Density 0.009%

    No Known Activations