© 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 EvalsExportsinterp-engineNEWAPI 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. 71169
    Prev
    Next
    INDEX
    Explanations

    阴

    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
    isters
    -0.08
    urations
    -0.08
    hinga
    -0.08
    gets
    -0.08
     Meth
    -0.08
     ruling
    -0.08
     misst
    -0.08
    Meth
    -0.08
    Clar
    -0.07
    سازی
    -0.07
    POSITIVE LOGITS
    쪽
    0.08
    shore
    0.08
     Lindsey
    0.07
    ર્ધ
    0.07
     investigator
    0.07
     favourable
    0.07
    -handed
    0.07
    幕后
    0.07
     inexperienced
    0.07
    ോട്ട്
    0.07
    Activations Density 0.004%

    No Known Activations