© 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. 11-RESID-POST-AA
    11. 111462
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    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
     Ae
    -0.08
     sør
    -0.07
     uh
    -0.07
     ವಿ�
    -0.07
     abe
    -0.07
    dbg
    -0.07
    brev
    -0.07
     Ví
    -0.07
     Philip
    -0.07
    aution
    -0.07
    POSITIVE LOGITS
    了一
    0.10
    了
    0.09
    ছে
    0.09
    ening
    0.09
    ાવે
    0.09
    ுகிறது
    0.09
    ించే
    0.09
     করছে
    0.09
     रखते
    0.09
    ப்படும்
    0.08
    Activations Density 0.394%

    No Known Activations