© 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. 44913
    Prev
    Next
    INDEX
    Explanations

    job/work/company

    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
     Foundation
    -0.08
     guda
    -0.08
     klin
    -0.08
     begleitet
    -0.07
     Initi
    -0.07
    ’ad
    -0.07
     실패
    -0.07
     команда
    -0.07
     admon
    -0.07
     নজ
    -0.07
    POSITIVE LOGITS
    નો
    0.10
     whereabouts
    0.09
    所属
    0.09
     проживания
    0.09
     tamaño
    0.09
     leeftijd
    0.09
     વર્ષ
    0.09
     grootte
    0.09
     อายุ
    0.09
     size
    0.09
    Activations Density 0.024%

    No Known Activations