© 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. 15-RESID-POST-AA
    11. 16439
    Prev
    Next
    INDEX
    Explanations

    coding and math problems

    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_15/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     найти
    -0.10
    ï
    -0.09
     trouver
    -0.09
     décider
    -0.09
     Entscheidungen
    -0.09
     encontrar
    -0.09
     déterminer
    -0.09
     determinar
    -0.08
     finding
    -0.08
     décidé
    -0.08
    POSITIVE LOGITS
    -inclusive
    0.08
    �
    0.08
    T
    0.08
    않
    0.08
    即可
    0.08
    Inclusive
    0.08
    Ghost
    0.08
    N
    0.08
     inclusive
    0.07
     infest
    0.07
    Activations Density 0.002%

    No Known Activations