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. 12999
    Prev
    Next
    INDEX
    Explanations

    wrist

    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
     priporoč
    -0.09
    icent
    -0.08
     treb
    -0.08
     heater
    -0.08
     COMPLETE
    -0.08
     newsp
    -0.08
    Wireless
    -0.07
     propulsion
    -0.07
     neće
    -0.07
     buoy
    -0.07
    POSITIVE LOGITS
     Eternal
    0.08
     essência
    0.08
     Må
    0.08
     autorização
    0.08
     eternal
    0.07
     Teknik
    0.07
    Thunk
    0.07
     تخصص
    0.07
    人
    0.07
     preliminary
    0.07
    Activations Density 0.001%

    No Known Activations