© 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. 102337
    Prev
    Next
    INDEX
    Explanations

    say "*" words

    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
     تعالى
    -0.08
    ancée
    -0.08
     చిత్రం
    -0.08
    -0.08
    ain
    -0.08
    çat
    -0.07
    oen
    -0.07
     படம்
    -0.07
    _ALWAYS
    -0.07
     yapı
    -0.07
    POSITIVE LOGITS
    개의
    0.12
     మంది
    0.11
     φορές
    0.10
    次
    0.10
    *sizeof
    0.10
     ಮಂದಿ
    0.10
     averages
    0.09
    -specific
    0.09
     codecs
    0.09
     jooksul
    0.09
    Activations Density 0.052%
    No Known Activations