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. 53888
    Prev
    Next
    INDEX
    Explanations

    急

    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
    Pra
    -0.08
    cand
    -0.08
    sic
    -0.07
    Dirty
    -0.07
    ými
    -0.07
    חור
    -0.07
    Pretty
    -0.07
    kušen
    -0.07
     everlasting
    -0.07
     Lauf
    -0.07
    POSITIVE LOGITS
    措施
    0.09
    niejs
    0.09
     �
    0.08
    急
    0.08
    用品
    0.08
    aneously
    0.08
    事项
    0.07
     sanitaire
    0.07
     �
    0.07
     suppressant
    0.07
    Activations Density 0.011%

    No Known Activations