© 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. 11-RESID-POST-AA
    11. 47493
    Prev
    Next
    INDEX
    Explanations

    presidential pardons

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ذية
    -0.08
    VC
    -0.08
    izwa
    -0.08
    ussi
    -0.08
    �
    -0.07
    ็บ
    -0.07
     captured
    -0.07
    pizza
    -0.07
    enuhi
    -0.07
    atisf
    -0.07
    POSITIVE LOGITS
     MAGIC
    0.08
     kindness
    0.08
     sins
    0.08
     Lamar
    0.07
    jobb
    0.07
     pard
    0.07
     konusunda
    0.07
    MAG
    0.07
     wars
    0.07
     Flor
    0.07
    Activations Density 0.007%

    No Known Activations