© 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. 21558
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    full
    -0.09
     donn
    -0.08
     "<
    -0.08
     induced
    -0.08
    mailer
    -0.08
    (full
    -0.07
    /"
    -0.07
    mapper
    -0.07
     voller
    -0.07
     ಸಂದರ್ಭದಲ್ಲಿ
    -0.07
    POSITIVE LOGITS
     други
    0.11
     другие
    0.11
     વગેરે
    0.11
     dalších
    0.11
     आदि
    0.11
     další
    0.11
     других
    0.11
     дигар
    0.10
     altres
    0.10
     etc
    0.10
    Activations Density 0.009%

    No Known Activations