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. 7-RESID-POST-AA
    6. 131070
    Prev
    Next
    INDEX
    Explanations

    without

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Добав
    -0.08
     производителя
    -0.08
     rollout
    -0.08
    787
    -0.08
     изготов
    -0.08
    삼
    -0.07
    arlar
    -0.07
     eingesch
    -0.07
     rede
    -0.07
     ​​
    -0.07
    POSITIVE LOGITS
    event
    0.08
    Muk
    0.07
     adanya
    0.07
     secours
    0.07
     mekan
    0.07
    Lou
    0.07
    多少
    0.07
    ewa
    0.07
    置
    0.07
     قوة
    0.07
    Activations Density 0.022%

    No Known Activations