© 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
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 12843
    Prev
    Next
    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_3/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Instead
    -0.07
     press
    -0.07
     appointment
    -0.07
     bewilder
    -0.07
    Nada
    -0.07
     الن
    -0.07
     Shaft
    -0.07
     darin
    -0.07
     abar
    -0.07
     Pew
    -0.07
    POSITIVE LOGITS
    BD
    0.08
    aha
    0.08
     BD
    0.08
     science
    0.08
    Ghost
    0.07
     dankzij
    0.07
    Science
    0.07
    .mn
    0.07
    ough
    0.07
     ghost
    0.07
    Activations Density 0.001%

    No Known Activations