© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 47729
    Prev
    Next
    INDEX
    Explanations

    antihypertensives

    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
     fire
    -0.08
    、大
    -0.08
     thighs
    -0.07
    Ker
    -0.07
     Kerala
    -0.07
     fmt
    -0.07
    حات
    -0.07
    园
    -0.07
     大
    -0.07
     Ker
    -0.07
    POSITIVE LOGITS
    pert
    0.11
    pertension
    0.09
    Pert
    0.08
     perturb
    0.08
     Pert
    0.08
     �
    0.08
    logic
    0.08
    ساس
    0.08
    loj
    0.08
    online
    0.07
    Activations Density 0.000%

    No Known Activations