© 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. 70953
    Prev
    Next
    INDEX
    Explanations

    undert

    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
    ाइज
    -0.08
    法人
    -0.08
     echte
    -0.07
     abr
    -0.07
    ogenic
    -0.07
     společnosti
    -0.07
    wesen
    -0.07
     dispersed
    -0.07
     dispers
    -0.07
    nict
    -0.07
    POSITIVE LOGITS
     subtle
    0.12
     tones
    0.11
    tones
    0.10
     accents
    0.10
     оттен
    0.10
     slight
    0.10
     subtly
    0.09
    -tone
    0.09
    贯
    0.08
     emphasis
    0.08
    Activations Density 0.014%

    No Known Activations