© 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. 50631
    Prev
    Next
    INDEX
    Explanations

    town

    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
     شہر
    -0.10
     городе
    -0.10
     ถนน
    -0.10
     شارع
    -0.10
     города
    -0.09
     şəh
    -0.09
    Roof
    -0.09
    แลนด์
    -0.09
     జిల్లా
    -0.09
     Skyline
    -0.09
    POSITIVE LOGITS
     doctor
    0.09
     ga
    0.08
     ditch
    0.08
     censor
    0.08
    .c
    0.08
    -common
    0.08
     defer
    0.08
     archives
    0.08
     limits
    0.08
     arbitration
    0.07
    Activations Density 0.005%

    No Known Activations