© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 19-RESID-POST-AA
    11. 18083
    Prev
    Next
    INDEX
    Explanations

    possessive words

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     or
    -0.10
     of
    -0.09
    、
    -0.08
     with
    -0.08
    /or
    -0.07
    、安全
    -0.07
     via
    -0.07
    /ou
    -0.07
    ಗಳಿಂದ
    -0.07
    ・
    -0.07
    POSITIVE LOGITS
    's
    0.15
    这一
    0.15
    自身
    0.13
     gesamten
    0.12
    整个
    0.12
     einzigartige
    0.12
     einzigart
    0.12
     સમગ્ર
    0.12
    这个
    0.12
     സ്വന്തം
    0.11
    Activations Density 0.025%

    No Known Activations