© 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. 23-RESID-POST-AA
    11. 5618
    Prev
    Next
    INDEX
    Explanations

    requ

    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_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    」。
    -0.08
     �
    -0.07
    _Def
    -0.07
    ODY
    -0.07
    ோக
    -0.07
    ocode
    -0.07
    OUND
    -0.07
    到了
    -0.07
    ستور
    -0.07
    ैनिक
    -0.07
    POSITIVE LOGITS
    ise
    0.12
    ises
    0.11
    ISE
    0.10
    imhse
    0.08
    érant
    0.08
    hatan
    0.08
     imprim
    0.07
     aérea
    0.07
    Sal
    0.07
     húmed
    0.07
    Activations Density 0.000%

    No Known Activations