Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 88172
    Prev
    Next
    INDEX
    Explanations

    Twitter/X

    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
     reconnect
    -0.08
     otherwise
    -0.08
    Otherwise
    -0.08
    틱
    -0.07
    otherwise
    -0.07
    _ble
    -0.07
    িষ্ঠ
    -0.07
    nij
    -0.07
     সম্প
    -0.07
     гри
    -0.07
    POSITIVE LOGITS
     district
    0.08
     kí
    0.07
     volleyball
    0.07
     conséquence
    0.07
    AMC
    0.07
    heastern
    0.07
     webmaster
    0.07
    府
    0.07
    226
    0.07
     clubs
    0.07
    Activations Density 0.000%

    No Known Activations