© 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. 19-RESID-POST-AA
    11. 102574
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
     관리
    -0.08
     static
    -0.07
     determ
    -0.07
    Altern
    -0.07
    Determ
    -0.07
     alternating
    -0.07
     kjen
    -0.07
     neben
    -0.07
     대표
    -0.07
     Betreuung
    -0.07
    POSITIVE LOGITS
    anduk
    0.09
     melakukan
    0.09
    됐
    0.09
     gerçekleşt
    0.09
     lakukan
    0.08
     ہوئی
    0.08
     జరిగింది
    0.08
     gedaan
    0.08
    angizo
    0.08
    âmica
    0.08
    Activations Density 0.002%

    No Known Activations