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. 97131
    Prev
    Next
    INDEX
    Explanations

    say "ac" words

    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
    sy
    -0.09
    yx
    -0.08
    syz
    -0.08
     verwe
    -0.08
     erat
    -0.07
    chid
    -0.07
     storm
    -0.07
    ändig
    -0.07
    োব
    -0.07
     chast
    -0.07
    POSITIVE LOGITS
    ac
    0.14
    	ac
    0.12
    _ac
    0.10
     التنظيم
    0.10
     cognitive
    0.09
    -ac
    0.09
    acic
    0.09
    -c
    0.09
    acs
    0.09
    /ac
    0.09
    Activations Density 0.001%

    No Known Activations