© 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. 25079
    Prev
    Next
    INDEX
    Explanations

    asbestos

    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
     vaik
    -0.08
    arin
    -0.08
     atraso
    -0.08
    akhala
    -0.08
    sap
    -0.08
     polo
    -0.07
    utad
    -0.07
    opause
    -0.07
     supaya
    -0.07
    وش
    -0.07
    POSITIVE LOGITS
     Canad
    0.08
     techniques
    0.08
     Crushing
    0.08
     aides
    0.08
     delic
    0.08
    ్డ
    0.08
     precautions
    0.08
    -card
    0.08
    Exercises
    0.07
     workouts
    0.07
    Activations Density 0.009%

    No Known Activations