© 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. 49270
    Prev
    Next
    INDEX
    Explanations

    M

    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
    ullan
    -0.07
     INTER
    -0.07
    organic
    -0.07
     Doppel
    -0.07
     LIMIT
    -0.07
    -таки
    -0.07
     Pou
    -0.07
    IN
    -0.07
     Orc
    -0.07
     уголов
    -0.07
    POSITIVE LOGITS
    ütte
    0.10
    adde
    0.09
    ாவ
    0.09
    ыйзам
    0.09
    ධ්
    0.08
    ித
    0.08
    بحث
    0.08
    ekana
    0.08
    قس
    0.08
    avio
    0.08
    Activations Density 0.001%

    No Known Activations