© 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. 102254
    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
    最后
    -0.08
     Maximum
    -0.08
     �
    -0.08
     \
    -0.08
     }\
    -0.08
     Gesamt
    -0.08
     }{@
    -0.08
     Total
    -0.08
     ``
    -0.08
    OTAL
    -0.08
    POSITIVE LOGITS
     person
    0.12
     persona
    0.12
     persoon
    0.12
     personne
    0.12
     thing
    0.12
     الشخص
    0.12
     code
    0.12
     idea
    0.12
     person's
    0.11
     pessoa
    0.11
    Activations Density 0.056%

    No Known Activations