© 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. 11-RESID-POST-AA
    11. 95463
    Prev
    Next
    INDEX
    Explanations

    sunscreen and water

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ifad
    -0.09
     ramp
    -0.08
     reflected
    -0.08
     rå
    -0.07
     pole
    -0.07
    .light
    -0.07
     Ramp
    -0.07
     triangle
    -0.07
     أفضل
    -0.07
     שת
    -0.07
    POSITIVE LOGITS
     때문에
    0.10
     entraîne
    0.08
    230
    0.08
    estrians
    0.08
    좌
    0.08
    bcrypt
    0.08
     వల్ల
    0.08
    違
    0.08
     entraîner
    0.08
    -http
    0.08
    Activations Density 0.016%

    No Known Activations