© 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. 11-RESID-POST-AA
    11. 95696
    Prev
    Next
    INDEX
    Explanations

    body fat

    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
     жаңа
    -0.09
    istema
    -0.08
     חדשים
    -0.08
    Conflict
    -0.08
    _runs
    -0.08
    ையாக
    -0.08
    -launch
    -0.08
     Preis
    -0.07
     дизайнер
    -0.07
     புதிய
    -0.07
    POSITIVE LOGITS
     obesity
    0.10
     abdominal
    0.09
    radius
    0.08
     zipcode
    0.08
     apron
    0.08
     الدهون
    0.08
     cortes
    0.08
     radius
    0.08
     suburbs
    0.08
     visceral
    0.08
    Activations Density 0.004%

    No Known Activations