© 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. 102271
    Prev
    Next
    INDEX
    Explanations

    Rounding numbers

    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
     controlar
    -0.09
    erialized
    -0.07
    -0.07
    enean
    -0.07
    _BL
    -0.07
    _Pl
    -0.07
    _EMPTY
    -0.07
    ormais
    -0.07
    _NULL
    -0.07
     reiterated
    -0.07
    POSITIVE LOGITS
     okuva
    0.10
     upgrading
    0.09
    but
    0.09
     lask
    0.09
    ៣
    0.09
     okkar
    0.09
     kuchokera
    0.09
    ერთ
    0.09
     მომ
    0.08
     yanu
    0.08
    Activations Density 0.005%
    No Known Activations