© 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. 23-RESID-POST-AA
    11. 51044
    Prev
    Next
    INDEX
    Explanations

    at

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_23/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     நிலைய
    -0.09
    igte
    -0.09
     মৃত্য
    -0.09
     predators
    -0.08
    retto
    -0.08
    ürlich
    -0.08
     ien
    -0.08
     मौत
    -0.08
    igde
    -0.08
     attachments
    -0.08
    POSITIVE LOGITS
    ology
    0.09
    iveness
    0.08
    <\/
    0.07
    iton
    0.07
     milit
    0.07
    oa
    0.07
    0.07
    <A
    0.07
     Grove
    0.07
    isayo
    0.07
    Activations Density 0.000%
    No Known Activations