© 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. 931
    Prev
    Next
    INDEX
    Explanations

    hand

    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
     Potion
    -0.09
     বিভ
    -0.09
     スーパー
    -0.08
     ভর্তি
    -0.08
     വിവാഹ
    -0.08
     włas
    -0.08
     นาย
    -0.08
     Gir
    -0.08
     પત્ન
    -0.08
     Ки
    -0.08
    POSITIVE LOGITS
     ethical
    0.09
    Qt
    0.08
    간
    0.07
    onitor
    0.07
     herein
    0.07
    도록
    0.07
    ethical
    0.07
    han
    0.07
    hacer
    0.07
    Wt
    0.07
    Activations Density 0.788%

    No Known Activations