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. 130874
    Prev
    Next
    INDEX
    Explanations

    say "uter"

    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
    IC
    -0.09
     ic
    -0.09
     gadget
    -0.08
    andy
    -0.08
    Comedy
    -0.08
    ’ég
    -0.08
    გომ
    -0.08
     अ
    -0.08
    Safari
    -0.08
     gadgets
    -0.08
    POSITIVE LOGITS
    uter
    0.20
     Bro
    0.10
    ut
    0.10
    utron
    0.10
    uta
    0.10
    bye
    0.10
    uters
    0.10
    utes
    0.10
    uti
    0.10
    tium
    0.09
    Activations Density 0.001%

    No Known Activations