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. 130970
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     خو
    -0.08
     fitte
    -0.08
     métr
    -0.08
    -medium
    -0.08
    etric
    -0.07
     ecosystem
    -0.07
    -million
    -0.07
     Histogram
    -0.07
    رير
    -0.07
     Monde
    -0.07
    POSITIVE LOGITS
    teacher
    0.09
     reconnaître
    0.08
     शिक्षक
    0.08
    orca
    0.08
    oxin
    0.08
    discussion
    0.08
    rection
    0.07
     শিক্ষক
    0.07
    orthand
    0.07
    ream
    0.07
    Activations Density 0.001%

    No Known Activations