© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 64192
    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
     અર્થ
    -0.08
     tarko
    -0.08
     meanings
    -0.08
    *:
    -0.07
     erity
    -0.07
    ulugan
    -0.07
    意义
    -0.07
     tähendab
    -0.07
     sizes
    -0.07
     significado
    -0.07
    POSITIVE LOGITS
    urne
    0.08
    BOUND
    0.08
    Comic
    0.08
     breeding
    0.08
     duplication
    0.08
     جاري
    0.08
     сезона
    0.08
     gyfr
    0.08
     entraîner
    0.08
     куз
    0.08
    Activations Density 0.001%

    No Known Activations