© 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. 30459
    Prev
    Next
    INDEX
    Explanations

    Simulator

    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
     regiones
    -0.09
     mip
    -0.08
     carreras
    -0.08
     advertisements
    -0.08
     ads
    -0.08
    arka
    -0.08
     adverts
    -0.07
     Artem
    -0.07
     increíbles
    -0.07
    观点
    -0.07
    POSITIVE LOGITS
    Cause
    0.08
    abcd
    0.08
     Dienstag
    0.07
    abc
    0.07
     causes
    0.07
    ³
    0.07
    Workout
    0.07
     affects
    0.07
     heißt
    0.07
     Cause
    0.07
    Activations Density 0.000%

    No Known Activations