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. 11912
    Prev
    Next
    INDEX
    Explanations

    know

    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
     благ
    -0.09
    forth
    -0.08
    -Ge
    -0.08
     گزارش
    -0.07
     приб
    -0.07
    095
    -0.07
     <<"
    -0.07
    _DISC
    -0.07
     blem
    -0.07
    067
    -0.07
    POSITIVE LOGITS
     ervan
    0.08
     টাকা
    0.07
    �
    0.07
     ث
    0.07
    业内
    0.07
    赚钱
    0.07
    ירת
    0.07
     spinach
    0.07
    钱
    0.07
    been
    0.07
    Activations Density 0.039%

    No Known Activations