© 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. 11-RESID-POST-AA
    11. 45253
    Prev
    Next
    INDEX
    Explanations

    from

    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
    etsk
    -0.09
    dued
    -0.09
     DU
    -0.07
     Sens
    -0.07
    _due
    -0.07
     Tack
    -0.07
     vanwege
    -0.07
     frag
    -0.07
    มาต
    -0.07
     modifiers
    -0.07
    POSITIVE LOGITS
     опыт
    0.08
    意见
    0.08
    经验
    0.08
     precedent
    0.08
     writings
    0.08
     lia
    0.07
     afar
    0.07
     выступ
    0.07
    akings
    0.07
     mistakes
    0.07
    Activations Density 0.024%

    No Known Activations