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. 11-RESID-POST-AA
    6. 11946
    Prev
    Next
    INDEX
    Explanations

    Consolid

    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
    ipv
    -0.08
     baza
    -0.08
    pressive
    -0.08
    yeah
    -0.08
     scrapy
    -0.08
    very
    -0.08
    assembly
    -0.07
    stall
    -0.07
    mao
    -0.07
    ATO
    -0.07
    POSITIVE LOGITS
     destinations
    0.08
     transferring
    0.08
     thunk
    0.08
     Emotion
    0.08
    0.07
    Synchron
    0.07
    encher
    0.07
     انتقال
    0.07
     concom
    0.07
     Zubehör
    0.07
    Activations Density 0.002%

    No Known Activations