Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · GPT-OSS BatchTopK SAEs
    3. GPT-OSS-20B
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 8969
    Prev
    Next
    INDEX
    Explanations

    punctuation

    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
     inversión
    -0.09
    ividual
    -0.08
     investimento
    -0.08
     dilo
    -0.07
    וכה
    -0.07
     проживания
    -0.07
     invertir
    -0.07
    ;b
    -0.07
    нэ
    -0.07
     gegn
    -0.07
    POSITIVE LOGITS
     ہمیں
    0.09
     যদি
    0.09
     직원
    0.08
     हमें
    0.08
     हमारे
    0.08
     ficaram
    0.08
     자신
    0.08
     malpractice
    0.08
     своим
    0.08
     synopsis
    0.08
    Activations Density 0.059%

    No Known Activations