© 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. 3-RESID-POST-AA
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    chance to

    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
     reform
    -0.08
     tubular
    -0.07
     whirl
    -0.07
     hung
    -0.07
    Continue
    -0.07
     Author
    -0.07
    .Team
    -0.07
     company
    -0.07
     team
    -0.07
     Public
    -0.07
    POSITIVE LOGITS
    য়
    0.08
    heater
    0.08
     bonos
    0.08
     Бас
    0.08
    δό
    0.08
     pprint
    0.08
     schwarz
    0.08
     bri
    0.08
     neurotrans
    0.08
    ，”
    0.08
    Activations Density 0.006%

    No Known Activations