© 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. 7-RESID-POST-AA
    11. 1121
    Prev
    Next
    INDEX
    Explanations

    over

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_7/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tier
    -0.08
    tier
    -0.08
    idwa
    -0.07
    _bin
    -0.07
    ollapse
    -0.07
     Bw
    -0.07
    ownika
    -0.07
    aray
    -0.07
    increment
    -0.07
     Increment
    -0.07
    POSITIVE LOGITS
    ాల్లో
    0.09
    ാമ
    0.09
     suede
    0.09
     поверхность
    0.09
     Oval
    0.08
    ాలకు
    0.08
     прокурат
    0.08
     поверхности
    0.08
    ాలి
    0.08
     పాల
    0.08
    Activations Density 0.010%

    No Known Activations