© 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. 47668
    Prev
    Next
    INDEX
    Explanations

    conver

    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
     стара
    -0.08
    _eq
    -0.08
     troca
    -0.08
     rencontre
    -0.07
     dot
    -0.07
    ಯ್ಯ
    -0.07
    _dot
    -0.07
     сентября
    -0.07
     возник
    -0.07
     nessa
    -0.07
    POSITIVE LOGITS
    gevens
    0.09
     DHS
    0.08
    üss
    0.08
    VN
    0.07
     paw
    0.07
    eel
    0.07
    部分
    0.07
     خور
    0.07
     microorganisms
    0.07
    Kd
    0.07
    Activations Density 0.000%

    No Known Activations