© 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. 68682
    Prev
    Next
    INDEX
    Explanations

    anabolic

    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
    रा
    -0.08
    แลนด์
    -0.07
     Wien
    -0.07
    -0.07
     vitrage
    -0.07
    Signed
    -0.07
    _signed
    -0.07
     Revenue
    -0.07
    erei
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     anabolic
    0.10
     hóa
    0.08
     estím
    0.08
     crot
    0.08
     abbreviated
    0.08
     vaik
    0.08
     affects
    0.08
     medis
    0.08
     globals
    0.07
     VM
    0.07
    Activations Density 0.001%
    No Known Activations