© 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. 19-RESID-POST-AA
    11. 18978
    Prev
    Next
    INDEX
    Explanations

    refers

    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_19/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     જેથી
    -0.09
     sehingga
    -0.09
    ५०
    -0.08
    蕉
    -0.08
     jotta
    -0.08
     जिससे
    -0.08
     waardoor
    -0.08
     nrog
    -0.08
     abbia
    -0.08
     puedan
    -0.08
    POSITIVE LOGITS
     refers
    0.26
     bezeichnet
    0.21
     என்பது
    0.20
    とは
    0.20
     adalah
    0.19
     বলতে
    0.19
     jechuun
    0.18
     म्हणजे
    0.18
     คือ
    0.17
     означает
    0.17
    Activations Density 0.138%

    No Known Activations