© 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. 51819
    Prev
    Next
    INDEX
    Explanations

    Being greater than

    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
    @endif
    -0.07
     achats
    -0.07
     senso
    -0.07
     buong
    -0.07
     endif
    -0.07
    akathi
    -0.07
    ി�
    -0.07
    ായി
    -0.06
     麻
    -0.06
     درمی
    -0.06
    POSITIVE LOGITS
     outweigh
    0.38
     overshadow
    0.36
     surpass
    0.34
     overpower
    0.34
     outperform
    0.33
     dominates
    0.33
     outwe
    0.32
     dominate
    0.32
     superar
    0.31
     eclips
    0.30
    Activations Density 0.154%

    No Known Activations