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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 97400
    Prev
    Next
    INDEX
    Explanations

    Materials testing

    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
     शीर्ष
    -0.08
     dispos
    -0.08
     vollständ
    -0.07
     traces
    -0.07
     dis
    -0.07
    geordnet
    -0.07
    -0.07
    Receipt
    -0.07
     inve
    -0.07
    azini
    -0.07
    POSITIVE LOGITS
     DMA
    0.08
     Netz
    0.08
     iod
    0.08
     simplex
    0.08
     pencil
    0.08
     DOG
    0.07
    Instr
    0.07
    万能
    0.07
    四
    0.07
    ТА
    0.07
    Activations Density 0.003%
    No Known Activations