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. 23-RESID-POST-AA
    6. 97992
    Prev
    Next
    INDEX
    Explanations

    Keywords or phrases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kork
    -0.08
    'imp
    -0.08
     أحداث
    -0.07
     TAB
    -0.07
    һын
    -0.07
     tem
    -0.07
     finns
    -0.07
    cheme
    -0.07
     Deutschlands
    -0.07
     daughter's
    -0.07
    POSITIVE LOGITS
     ഇൻ
    0.07
    客户端
    0.07
    腰
    0.07
    .value
    0.07
    OSS
    0.07
    ary
    0.07
     ഇന്
    0.07
     fiddle
    0.07
    ôs
    0.07
     ‪
    0.07
    Activations Density 0.001%

    No Known Activations