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. 60688
    Prev
    Next
    INDEX
    Explanations

    Asking questions, conversation

    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
     distilled
    -0.08
     আদাল
    -0.07
     prél
    -0.07
    剤
    -0.07
    纪律
    -0.07
     unfor
    -0.07
     neglig
    -0.07
     الجودة
    -0.07
     تدخل
    -0.07
    _Msk
    -0.07
    POSITIVE LOGITS
     hobbies
    0.15
     hobby
    0.12
     anecdotes
    0.12
     趣
    0.11
    分享
    0.11
     erzählen
    0.11
    交流
    0.11
     Turk
    0.11
    趣
    0.11
     haqqında
    0.10
    Activations Density 0.049%

    No Known Activations