© 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. 51227
    Prev
    Next
    INDEX
    Explanations

    Ansible configuration files

    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
     remover
    -0.08
     remercie
    -0.08
     retirer
    -0.08
     الماء
    -0.08
     souhaitent
    -0.08
     Cler
    -0.08
     gəl
    -0.08
    invite
    -0.08
    KER
    -0.08
     invite
    -0.07
    POSITIVE LOGITS
     yose
    0.08
    zn
    0.08
     yone
    0.08
     Samm
    0.08
     replaced
    0.08
     Aure
    0.07
     eucalyptus
    0.07
     lambda
    0.07
    zne
    0.07
     sund
    0.07
    Activations Density 0.000%

    No Known Activations