© 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. 51443
    Prev
    Next
    INDEX
    Explanations

    treatment

    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
     newsroom
    -0.08
    igol
    -0.08
    enson
    -0.07
    셜
    -0.07
     cartão
    -0.07
     studenten
    -0.07
     Bazaar
    -0.07
     mochila
    -0.07
     pedestrians
    -0.07
     citiz
    -0.07
    POSITIVE LOGITS
     treatment
    0.69
    Treatment
    0.63
     Treatment
    0.63
     tratamiento
    0.62
     treatments
    0.62
     tratamento
    0.61
     ಚಿಕಿತ್ಸೆ
    0.59
     उपचार
    0.59
    治疗
    0.59
     સારવાર
    0.59
    Activations Density 0.179%

    No Known Activations