© 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. 78263
    Prev
    Next
    INDEX
    Explanations

    sub

    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
     спис
    -0.08
     NSCoder
    -0.08
     bends
    -0.07
    //*[@
    -0.07
     చర్య
    -0.07
     pivotal
    -0.07
     ruler
    -0.07
     wife's
    -0.07
     kapcsolat
    -0.07
     систем
    -0.07
    POSITIVE LOGITS
    Pair
    0.10
    组成
    0.10
    _pair
    0.10
    Pairs
    0.09
    (component
    0.08
    Sens
    0.08
     pairing
    0.08
    _hi
    0.08
     саме
    0.08
    组件
    0.08
    Activations Density 0.004%

    No Known Activations