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. 43953
    Prev
    Next
    INDEX
    Explanations

    duality

    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
    quire
    -0.08
     Aim
    -0.07
     Kick
    -0.07
    Dropped
    -0.07
    Kent
    -0.07
     Told
    -0.07
     jig
    -0.07
     인증
    -0.07
     chaining
    -0.07
    Rc
    -0.07
    POSITIVE LOGITS
     oppos
    0.13
     opposing
    0.12
     contrasting
    0.12
     opposite
    0.12
     противоп
    0.12
     अच्छ
    0.10
     dich
    0.10
    �
    0.09
     antagon
    0.09
     играет
    0.09
    Activations Density 0.024%

    No Known Activations