© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 16281
    Prev
    Next
    INDEX
    Explanations

    Possessive pronoun

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ментов
    -0.09
    ъти
    -0.09
     tačiau
    -0.09
    .Tags
    -0.08
    _CLASSES
    -0.08
    نوعة
    -0.08
    ڼ
    -0.08
    (errno
    -0.08
    аларын
    -0.08
    альних
    -0.08
    POSITIVE LOGITS
    's
    0.10
    ’s
    0.09
     object's
    0.09
     city's
    0.08
     school's
    0.08
     company's
    0.08
     country's
    0.08
     application's
    0.07
     article
    0.07
    -created
    0.07
    Activations Density 0.013%

    No Known Activations