© 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. 129275
    Prev
    Next
    INDEX
    Explanations

    minimalist marketing

    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
    ATIONS
    -0.09
     olmay
    -0.08
     julgamento
    -0.08
     rikt
    -0.08
    169
    -0.08
     erb
    -0.07
    不起
    -0.07
    ITIES
    -0.07
    least
    -0.07
     फार
    -0.07
    POSITIVE LOGITS
     ensuring
    0.07
    èin
    0.07
     ♥
    0.07
     notre
    0.07
     Tribune
    0.07
     our
    0.07
    озн
    0.07
    ουμε
    0.07
     Coun
    0.07
    ানো
    0.07
    Activations Density 0.136%

    No Known Activations