© 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. 50697
    Prev
    Next
    INDEX
    Explanations

    say "4 or 0" numbers

    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
     fest
    -0.08
    ueil
    -0.08
     להג
    -0.08
     Congress
    -0.08
     लिह
    -0.08
     दिने
    -0.08
     ilaal
    -0.08
    osamente
    -0.08
     kirjut
    -0.08
     диҳ
    -0.08
    POSITIVE LOGITS
    47
    0.08
    оп
    0.08
    PN
    0.07
    ოპ
    0.07
    094
    0.07
    471
    0.07
    475
    0.07
    ocal
    0.07
     Smarty
    0.07
    942
    0.07
    Activations Density 0.015%

    No Known Activations