© 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. 5433
    Prev
    Next
    INDEX
    Explanations

    р

    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
    эль
    -0.11
    э
    -0.10
    цы
    -0.09
    Э
    -0.09
     lub
    -0.09
    ограмм
    -0.09
    альные
    -0.09
    альную
    -0.09
    lhe
    -0.09
    ель
    -0.09
    POSITIVE LOGITS
     други
    0.16
    ални
    0.14
     използ
    0.14
     елип
    0.14
     които
    0.14
    ън
    0.14
    ър
    0.14
     съд
    0.14
    ъп
    0.14
     който
    0.14
    Activations Density 0.003%

    No Known Activations