© 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. 68363
    Prev
    Next
    INDEX
    Explanations

    progress and setbacks

    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
    algia
    -0.08
    료
    -0.08
     eignet
    -0.08
     ratt
    -0.07
     magaz
    -0.07
     heißt
    -0.07
     booklet
    -0.07
     divent
    -0.07
     lautet
    -0.07
     "*
    -0.07
    POSITIVE LOGITS
     Fortsch
    0.17
     progress
    0.16
     progreso
    0.15
    	progress
    0.15
     progresso
    0.14
     progrès
    0.14
     Progress
    0.14
     advancements
    0.14
     strides
    0.13
     progressed
    0.13
    Activations Density 0.052%

    No Known Activations