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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18294
    Prev
    Next
    INDEX
    Explanations

    Repetition

    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
    cieš
    -0.11
    前年差
    -0.09
     tsjin
    -0.09
    ＼(^
    -0.09
    упить
    -0.09
     таъмин
    -0.09
    лиги
    -0.09
     ausreich
    -0.08
    รั่ง
    -0.08
    აუდ
    -0.08
    POSITIVE LOGITS
     repeatedly
    0.30
     continually
    0.22
     repet
    0.19
     continuously
    0.19
    Repeated
    0.19
     constantly
    0.18
     constantemente
    0.17
     continuamente
    0.17
     constamment
    0.17
     periodically
    0.17
    Activations Density 0.025%

    No Known Activations