© 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. 94583
    Prev
    Next
    INDEX
    Explanations

    safe

    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
    (ph
    -0.09
     Mull
    -0.08
     coloured
    -0.08
     ചോദ
    -0.08
     Chapel
    -0.07
    clair
    -0.07
     First
    -0.07
     gefragt
    -0.07
     diagram
    -0.07
    diagram
    -0.07
    POSITIVE LOGITS
     surpass
    0.11
     exceeds
    0.10
     exceed
    0.10
    超过
    0.09
     একটু
    0.09
     dépasse
    0.09
    র্ঘ
    0.09
     exceeding
    0.09
     memenuhi
    0.09
     تجاوز
    0.09
    Activations Density 0.015%

    No Known Activations