© 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. 68696
    Prev
    Next
    INDEX
    Explanations

    {

    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
    割
    -0.09
    搬
    -0.08
    -eyed
    -0.08
    wired
    -0.07
     Petrol
    -0.07
    Certified
    -0.07
     Faro
    -0.07
     nghĩa
    -0.07
    ített
    -0.07
     澳洲
    -0.07
    POSITIVE LOGITS
    120
    0.08
    967
    0.08
     сюда
    0.07
    158
    0.07
    .apache
    0.07
     rechts
    0.07
     drücken
    0.07
     Ta
    0.07
     tp
    0.07
     номер
    0.07
    Activations Density 0.004%

    No Known Activations