© 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. 97885
    Prev
    Next
    INDEX
    Explanations

    unknown token

    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
    校
    -0.09
    algia
    -0.08
     Mestre
    -0.08
     domine
    -0.08
    asu
    -0.07
    arry
    -0.07
    domést
    -0.07
    oland
    -0.07
     kier
    -0.07
    �
    -0.07
    POSITIVE LOGITS
    �
    0.15
    ાથ
    0.09
    处分
    0.08
    ्प
    0.08
    ">%
    0.08
    ਥ
    0.08
     пол
    0.08
    处
    0.08
     SENT
    0.07
     senti
    0.07
    Activations Density 0.000%

    No Known Activations