© 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. 54546
    Prev
    Next
    INDEX
    Explanations

    under

    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
    대로
    -0.09
    幅
    -0.08
     lighten
    -0.08
    而言
    -0.07
    Victoria
    -0.07
     strawberries
    -0.07
     tran
    -0.07
     onset
    -0.07
     finit
    -0.07
    _sec
    -0.07
    POSITIVE LOGITS
    pins
    0.10
    estim
    0.09
    stood
    0.09
    halb
    0.09
    Expose
    0.08
    DEBUG
    0.08
    whel
    0.08
     scrutiny
    0.08
    lies
    0.08
    perform
    0.08
    Activations Density 0.061%

    No Known Activations