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. 11-RESID-POST-AA
    6. 88305
    Prev
    Next
    INDEX
    Explanations

    lo

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.09
    iov
    -0.08
    版
    -0.08
    stood
    -0.08
     Limb
    -0.07
    Bg
    -0.07
    ]])↵
    -0.07
    Oops
    -0.07
    POS
    -0.07
    现场
    -0.07
    POSITIVE LOGITS
     mot
    0.08
    ווה
    0.08
    alter
    0.08
     wi
    0.08
     sé
    0.07
     serv
    0.07
     perd
    0.07
     defined
    0.07
     ginger
    0.07
     cer
    0.07
    Activations Density 0.009%

    No Known Activations